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. 12714
    Prev
    Next
    INDEX
    Explanations

    One

    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
     year's
    -0.08
     ensuing
    -0.08
    年度
    -0.08
     җ
    -0.07
    Notifications
    -0.07
    കർ
    -0.07
    avras
    -0.07
     Edith
    -0.07
     Windsor
    -0.07
    Survey
    -0.07
    POSITIVE LOGITS
     Seems
    0.09
     div
    0.08
     والث
    0.07
    轴
    0.07
    芸
    0.07
    さ
    0.07
     જાય
    0.07
    mol
    0.07
    heit
    0.07
     madre
    0.07
    Activations Density 0.006%

    No Known Activations