REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features
Steering with Sparse Autoencoders (SAEs) offers a lightweight inference-time path for adapting the behavior of large language models without retraining. By exposing sparse and interpretable features, SAE steering provides a promising interface for safety control that guides harmful continuations toward refusal. However, we observe that complex wrappers can still undermine existing SAE steering methods on harmful prompts. To evaluate this failure mode systematically, we construct Generalized Undercover Instruction Safety Evaluation (GUISE), a dataset of harmful prompts with complex wrappers. Existing single direction SAE steering methods do not reliably produce refusals on harmful prompts,...
| Authors | Kai-Xuan Ding, Hao-Xiang Xu, Ji-Hua Peng et al. |
|---|---|
| Primary category | cs.AI |
| Published | 28 August 2026 |
| Last updated at source | 28 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.