Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56056
    Prev
    Next
    INDEX
    Explanations

    revolution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     earm
    -0.08
    endpoint
    -0.08
     irreversible
    -0.07
     endpoint
    -0.07
    javascript
    -0.07
     einzigartige
    -0.07
    allocate
    -0.07
    war
    -0.07
     Unique
    -0.07
     Arrays
    -0.07
    POSITIVE LOGITS
     作者
    0.08
     toss
    0.08
     vies
    0.08
    нуться
    0.08
     trovare
    0.08
    წლ
    0.08
     满堂
    0.08
     nny
    0.08
     Bahamas
    0.08
     boosting
    0.07
    Activations Density 0.011%

    No Known Activations