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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45856
    Prev
    Next
    INDEX
    Explanations

    Guru

    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
     sidewalks
    -0.10
     bureaucracy
    -0.09
     département
    -0.09
     bachelor's
    -0.09
     drywall
    -0.09
     bathrooms
    -0.09
     Sheriff's
    -0.08
     Lawyers
    -0.08
     subsidy
    -0.08
     الأردن
    -0.08
    POSITIVE LOGITS
     revered
    0.09
     gurus
    0.08
    Ист
    0.08
    0.08
    嘉
    0.07
    แก่
    0.07
     بزرگ
    0.07
    اضر
    0.07
     Gener
    0.07
    .guid
    0.07
    Activations Density 0.018%

    No Known Activations