# OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

arXiv: https://arxiv.org/abs/2509.22033 · HTML: https://mlsanity.com/paper/2509.22033/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Sparse autoencoder training and evaluation, one of 13 directions in Mechanistic interpretability.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- Mechanistic interpretability / [Sparse autoencoder training and evaluation](https://mlsanity.com/mechinterp/sparse-autoencoder-training-and-evaluation/)

## Builds on (most cited first, 21 of 21)

- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024)
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2409.14507/) (2024)
- [Learning Multi-Level Features with Matryoshka Sparse Autoencoders](https://mlsanity.com/paper/2503.17547/) (2025)
- [BatchTopK Sparse Autoencoders](https://mlsanity.com/paper/2412.06410/) (2024)
- [SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability](https://mlsanity.com/paper/2503.09532/) (2025)
- [Automatically Interpreting Millions of Features in Large Language Models](https://mlsanity.com/paper/2410.13928/) (2024)
- [Reducing Overfitting in Deep Networks by Decorrelating Representations](https://mlsanity.com/paper/1511.06068/) (2015)
- [Sparse Autoencoders Do Not Find Canonical Units of Analysis](https://mlsanity.com/paper/2502.04878/) (2025)
- [RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations](https://mlsanity.com/paper/2402.17700/) (2024)
- [A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models](https://mlsanity.com/paper/2503.05613/) (2025)
- [Regularizing CNNs with Locally Constrained Decorrelations](https://mlsanity.com/paper/1611.01967/) (2016)
- [Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers](https://mlsanity.com/paper/2501.17727/) (2025)
- [Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders](https://mlsanity.com/paper/2505.11756/) (2025)
- [MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles](https://mlsanity.com/paper/2006.06527/) (2020)

## Built on by (most cited first, 8 of 8)

- [Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?](https://mlsanity.com/paper/2602.14111/) (2026)
- [From Atoms to Trees: Building a Structured Feature Forest with Hierarchical Sparse Autoencoders](https://mlsanity.com/paper/2602.11881/) (2026)
- [Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models](https://mlsanity.com/paper/2602.04718/) (2026)
- [C2R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2606.30609/) (2026)
- [A Deeper Analysis of Block-Sparse Featurizers](https://mlsanity.com/paper/2608.27515/) (2026)
- [Interference Beyond Geometry in Concept Extraction](https://mlsanity.com/paper/2609.35351/) (2026)
- [When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders](https://mlsanity.com/paper/2609.36294/) (2026)
- [Towards Fast and Disentangled Counterfactuals for Visual Foundation Models](https://mlsanity.com/paper/2610.00895/) (2026)

## Abstract (arXiv)

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of general features creating representation holes, and feature composition, where independent features merge into composite representations. In this work, we introduce Orthogonal SAE (OrtSAE), a novel approach aimed to mitigate these issues by enforcing orthogonality between the learned features. By implementing a new training procedure that penalizes high pairwise cosine similarity between SAE features, OrtSAE promotes the development of disentangled features while scaling linearly with the SAE size, avoiding significant computational overhead. We train OrtSAE across different models and layers and compare it with other methods. We find that OrtSAE discovers 9% more distinct features, reduces feature absorption (by 65%) and composition (by 15%), improves performance on spurious correlation removal (+6%), and achieves on-par performance for other downstream tasks compared to traditional SAEs.