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. 112880
    Prev
    Next
    INDEX
    Explanations

    Doubt/Uncertainty

    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
    Jun
    -0.08
    종
    -0.08
    _definition
    -0.08
     yine
    -0.07
    .Butter
    -0.07
    _mov
    -0.07
    522
    -0.07
     ಏ
    -0.07
     എന്ത
    -0.07
    Aw
    -0.07
    POSITIVE LOGITS
     obvious
    0.09
     bæ
    0.08
     fabulous
    0.08
     сор
    0.07
     folly
    0.07
     bruk
    0.07
    ,更
    0.07
    ulde
    0.07
     прекрас
    0.07
     druk
    0.07
    Activations Density 0.011%

    No Known Activations