Sparse Autoencoders for Interpretable Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2607.12094v1
• Date: Mon, 13 Jul 2026 19:13:40 GMT
• Title: Sparse Autoencoders for Interpretable Out-of-Distribution Detection
• Abstract summary: This paper introduces a novel approach that leverages sparse autoencoders (SAEs) to learn interpretable features from intermediate activations.<n>We propose a new OOD score derived from the cosine similarity between the sparse feature activations of a test sample and the mean activations of ID classes.
• Score: 5.034534322537894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models. Neural networks often produce overconfident predictions for inputs that deviate from their training data, leading to significant degradation in performance. While many OOD detection methods focus on the final output layer, they neglect the rich hierarchical information present in intermediate network layers. This paper introduces a novel approach that leverages sparse autoencoders (SAEs) to learn interpretable features from these intermediate activations. We find that in-distribution (ID) and OOD data activate distinct sets of these sparse features. We propose a new OOD score derived from the cosine similarity between the sparse feature activations of a test sample and the mean activations of ID classes. Our post-hoc detection method not only achieves state-of-the-art performance on standard OOD detection benchmarks, but yields interpretable insights into how distribution shift affects learned representations.

Related papers

• Revisiting Logit Distributions for Reliable Out-of-Distribution Detection [73.9121001113687]
  Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications.<n>LogitGap is a novel post-hoc OOD detection method that exploits the relationship between the maximum logit and the remaining logits.<n>We show that LogitGap consistently achieves state-of-the-art performance across diverse OOD detection scenarios and benchmarks.
  arXiv  Detail & Related papers  (2025-10-23T02:16:45Z)
• What If the Input is Expanded in OOD Detection? [77.37433624869857]
  Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. We introduce a novel perspective, i.e., employing different common corruptions on the input space.
  arXiv  Detail & Related papers  (2024-10-24T06:47:28Z)
• FlowCon: Out-of-Distribution Detection using Flow-Based Contrastive Learning [0.0]
  We introduce textitFlowCon, a new density-based OOD detection technique. Our main innovation lies in efficiently combining the properties of normalizing flow with supervised contrastive learning. Empirical evaluation shows the enhanced performance of our method across common vision datasets.
  arXiv  Detail & Related papers  (2024-07-03T20:33:56Z)
• EAT: Towards Long-Tailed Out-of-Distribution Detection [55.380390767978554]
  This paper addresses the challenging task of long-tailed OOD detection. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes. We propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes, and (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data.
  arXiv  Detail & Related papers  (2023-12-14T13:47:13Z)
• Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection [27.062465089674763]
  Out-of-distribution (OOD) detection is essential when deploying neural networks in the real world. One main challenge is that neural networks often make overconfident predictions on OOD data. We propose an effective post-hoc OOD detection method based on a new feature masking strategy and a novel logit smoothing strategy.
  arXiv  Detail & Related papers  (2023-10-27T12:42:17Z)
• A Functional Data Perspective and Baseline On Multi-Layer Out-of-Distribution Detection [30.499548939422194]
  Methods that explore the multiple layers either require a special architecture or a supervised objective to do so. This work adopts an original approach based on a functional view of the network that exploits the sample's trajectories through the various layers and their statistical dependencies. We validate our method and empirically demonstrate its effectiveness in OOD detection compared to strong state-of-the-art baselines on computer vision benchmarks.
  arXiv  Detail & Related papers  (2023-06-06T09:14:05Z)
• Improving Out-of-Distribution Detection with Disentangled Foreground and Background Features [23.266183020469065]
  We propose a novel framework that disentangles foreground and background features from ID training samples via a dense prediction approach. It is a generic framework that allows for a seamless combination with various existing OOD detection methods.
  arXiv  Detail & Related papers  (2023-03-15T16:12:14Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Beyond Mahalanobis-Based Scores for Textual OOD Detection [32.721317681946246]
  We introduce TRUSTED, a new OOD detector for classifiers based on Transformer architectures that meets operational requirements. The efficiency of TRUSTED relies on the fruitful idea that all hidden layers carry relevant information to detect OOD examples. Our experiments involve 51k model configurations, including various checkpoints, seeds, datasets, and demonstrate that TRUSTED achieves state-of-the-art performances.
  arXiv  Detail & Related papers  (2022-11-24T10:51:58Z)
• Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities [104.02531442035483]
  The goal of this paper is to recognize common objectives as well as to identify the implicit scoring functions of different OOD detection methods. We show that binary discrimination between in- and (different) out-distributions is equivalent to several distinct formulations of the OOD detection problem. We also show that the confidence loss which is used by Outlier Exposure has an implicit scoring function which differs in a non-trivial fashion from the theoretically optimal scoring function.
  arXiv  Detail & Related papers  (2022-06-20T16:32:49Z)
• Igeood: An Information Geometry Approach to Out-of-Distribution Detection [35.04325145919005]
  We introduce Igeood, an effective method for detecting out-of-distribution (OOD) samples. Igeood applies to any pre-trained neural network, works under various degrees of access to the machine learning model. We show that Igeood outperforms competing state-of-the-art methods on a variety of network architectures and datasets.
  arXiv  Detail & Related papers  (2022-03-15T11:26:35Z)
• Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation [76.2621758731288]
  We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA) We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
  arXiv  Detail & Related papers  (2021-08-03T17:09:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.