Calibrating Lightweight Sparse Autoencoder Feature Steering

Sparse autoencoders (SAEs) can enable inference-time topic steering by modifying latent feature activations, but existing steering methods often fail when target-aligned features are not identified or are modified at the wrong scale. We introduce textscContrastiveSteer to address these respective failure modes. First, features are scored by how much more strongly they activate on target-domain text than on general text. Second, steering strength is set using a model-specific calibration. We also introduce contamination, a complementary heuristic that measures whether post-steering activations emphasize weakly aligned features, thus indicating off-target or nonsensical outputs. In our evaluations, across multiple LLM families and SAEs, textscContrastiveSteer improves topic alignment across domains up to 3.9× over unsteered and steering baselines, and raises target-domain classification by up to 93%. Our activation-scale normalization method also recovers at least 93% of optimal domain-score gains across all tested model families, and contamination distinguishes successful steering, under-steering, and over-steering collapse.