# A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy

arXiv: https://arxiv.org/abs/2601.18939 · HTML: https://mlsanity.com/paper/2601.18939/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 7 of 7)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Simple synthetic data reduces sycophancy in large language models](https://mlsanity.com/paper/2308.03958/) (2023)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)
- [From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning](https://mlsanity.com/paper/2409.01658/) (2024)
- [Talking Heads: Understanding Inter-layer Communication in Transformer Language Models](https://mlsanity.com/paper/2406.09519/) (2024)

## Built on by (most cited first, 2 of 2)

- [The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration](https://mlsanity.com/paper/2605.18372/) (2026)
- [THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts](https://mlsanity.com/paper/2608.15687/) (2026)

## Abstract (arXiv)

Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that identifies and updates only the neurons most responsible for a given behavior, a targeted approach that allows for fine-tuning with significantly less data. Using sparse autoencoders (SAEs) and linear probes, we isolate the 3% of MLP neurons most predictive of a target behavior, decode them into residual space, and fine-tune only those neurons using gradient masking. We demonstrate this approach on the task of reducing sycophantic behavior, where our method matches or exceeds state-of-the-art performance on four benchmarks (Syco-Bench, NLP, POLI, PHIL) using Gemma-2-2B and 9B models. Our results show that sparse, neuron-level updates offer a scalable and precise alternative to full-model fine-tuning, remaining effective even in situations when little data is available