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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8290
    Prev
    Next
    INDEX
    Explanations

    code headers

    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
     بالخ
    -0.10
     voluntad
    -0.09
     לדבר
    -0.09
     Voyager
    -0.08
     Tarot
    -0.08
     للخ
    -0.08
     midd
    -0.08
     coer
    -0.08
    נסות
    -0.08
     tapis
    -0.08
    POSITIVE LOGITS
    =headers
    0.11
    clang
    0.11
     clang
    0.10
     headers
    0.10
    .headers
    0.10
    文件
    0.09
    _headers
    0.09
    /header
    0.09
     header
    0.09
    .hpp
    0.09
    Activations Density 0.010%

    No Known Activations