这篇论文用大量对比实验告诉你：训练方法不同，模型可解释性天差地别。想用模型有机体做可解释性研究的话，得先看看训练方式合不合适。
研究构建了54个基于OLMo2-1B和gemma-3-1b-it的模型有机体，采用7种不同训练技术（包括后训练SFT、DPO以及更现实的集成训练）。通过激活oracle、激活引导、logit lens和稀疏自编码器等基准测试发现，模型有机体的可解释性强烈依赖于训练目标、目标行为、模型架构和数据生成流程。即使控制目标行为表达强度，各条件下的可解释性方差依然显著。更现实的集成训练方法往往比标准后训练方法产生更不可解释的模型有机体。这些结果质疑了当前模型有机体作为可解释性代理的有效性。
The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques. Current MOs are typically constructed via post-hoc supervised fine-tuning (SFT) on behavioural transcripts or synthetic documents. Prior research has shown that interpretability methods can easily identify hidden behaviours in these MOs. However, recent work suggests that such post-hoc training methods may make interpretability unrealistically easy. We investigate this claim by constructing a suite of 54 $\verb|OLMo2-1B|$- and $\verb|gemma-3-1b-it|$-based MOs trained with seven different techniques, including standard post-hoc SFT, post-hoc DPO, and more realistic integration of MO data into the OLMo post-training DPO phase. We use these MO variants to benchmark activation oracles, activation steering, logit lens, and sparse autoencoders. Our findings show that (i) MO interpretability depends strongly on training objective, target behaviour, model architecture, and training data generation pipeline; (ii) substantial variance remains even after controlling for differences in the strength of target behaviour expression; and (iii) our more realistic $\textit{integrated training}$ often yields less interpretable MOs than standard post-hoc methods. Our results cast substantial doubt on the validity of current MOs as interpretability proxies.