A python implementation inspired by SAE-TM
@LGirrbach is already working on this.
Since Jun 21, 2026.
Assessment
This issue has not been assessed yet.
Description
Hi @LGirrbach ,
Thanks for the work and the code release. I built an unofficial Python package inspired by the paper and this repository: SAETopic. It exposes SAE topic atoms through a package-oriented interface, with an API style inspired by BERTopic for fitting, topic inspection, save/load, and changing topic granularity without retraining.
I’m sharing it here in case it is useful to others experimenting with SAE-TM, and I’d be happy to adjust attribution or wording if you prefer.
Thanks again.
- Dominant language
- Jupyter Notebook
- Stars
- 10
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from ExplainableML/SAE-TM
-
Code for caption generationMay be free again @LGirrbach claimed this 111 days ago, and no pull request is open. Open
ExplainableML/SAE-TM#1 · 1 comment · 1 assignee ·