# Bypass Observation: A Conceptual Design of a Non-Intrusive Layer-Wise Semantic Extraction Architecture

arXiv: https://arxiv.org/abs/2609.13807 · HTML: https://mlsanity.com/paper/2609.13807/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [Looped Transformers as Programmable Computers](https://mlsanity.com/paper/2301.13196/) (2023)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)

## Abstract (arXiv)

Large language models reason in high-dimensional hidden-state spaces, while users observe only final outputs. We introduce Bypass Observation, a non-intrusive layer-wise readout architecture that attaches read-only observation heads to selected Transformer layers without feeding their outputs back into the backbone. We consider three variants: a shared LM head across layers, layer-specific heads, and a layer- or step-adaptive head. For full-vocabulary readout, we derive a closed-form overhead approximation governed primarily by V/(12d), with representative estimates ranging from about 30% to 240%, and discuss cost reductions via sparse observation, low-rank factorization, reduced vocabularies, top-k readout, and selective positions. We argue that Bypass Observation can make model computation more observable while remaining only a partial, potentially misleading projection of hidden states. We further distinguish bypass chain-of-thought from conventional chain-of-thought: conventional reasoning tokens enter the autoregressive computation, whereas bypass readouts remain causally external at inference time, although they can still provide training signals in reinforcement learning. Finally, we discuss applications to looped and recurrent-depth Transformers, where iteration-wise readout may expose convergence, oscillation, and potential halting signals. The proposal is conceptual and analytical; systematic empirical validation remains future work.