Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations based on top activating input examples, we present a fundamentally different alternative based on causal interventions. We leverage the structure of Vision-Language Models and steer individual SAE features in the vision encoder after providing an empty image. Then, we prompt the language model to explain what it ``sees'', effectively eliciting the visual concept represented by each feature. Results show that Steering offers an scalable alternative that complements traditional approaches based on input examples, serving as a new axis for automated interpretability in vision models. Moreover, the quality of explanations improves consistently with the scale of the language model, highlighting our method as a promising direction for future research. Finally, we propose Steering-informed Top-k, a hybrid approach that combines the strengths of causal interventions and input-based approaches to achieve state-of-the-art explanation quality without additional computational cost.
@article{arxiv.2603.22593,
title = {Language Models Can Explain Visual Features via Steering},
author = {Javier Ferrando and Enrique Lopez-Cuena and Pablo Agustin Martin-Torres and Daniel Hinjos and Anna Arias-Duart and Dario Garcia-Gasulla},
journal= {arXiv preprint arXiv:2603.22593},
year = {2026}
}