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
15-RESID-POST-AA
40
Prev
Next
MODEL
15-resid-post-aa
Source/SAE
INDEX
Go
Explanations
value
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_15/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/15-resid-post-aa/40?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt-oss-20b/15-resid-post-aa/40?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
」です
-0.11
。此外
-0.09
。不过
-0.08
입니다
-0.08
”的
-0.08
。这
-0.08
。另外
-0.08
。然而
-0.08
。因此
-0.08
。所以
-0.08
POSITIVE LOGITS
，然后
0.22
，并
0.19
แล้ว
0.18
했고
0.17
並
0.16
然后
0.15
sannan
0.15
并
0.15
చేసి
0.14
banjur
0.14
Act
ivations
Density 0.266%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
