Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
23-RESID-POST-AA
98066
Prev
Next
MODEL
23-resid-post-aa
Source/SAE
INDEX
Go
Explanations
。
np_max-act-logits · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
Dataset (Dashboard)
Various
No Configuration Found
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt-oss-20b/23-resid-post-aa/98066?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt-oss-20b/23-resid-post-aa/98066?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
，该
-0.09
-0.09
Addon
-0.08
/T
-0.08
/P
-0.08
Due
-0.08
primarily
-0.08
(I
-0.08
mainly
-0.08
due
-0.08
POSITIVE LOGITS
我们
0.19
那些
0.18
如果
0.18
우리가
0.18
事实上
0.17
有人
0.17
우리는
0.17
这是
0.17
ನಾವು
0.17
이것
0.17
Act
ivations
Density 0.046%
Test
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
