© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102958
    Prev
    Next
    INDEX
    Explanations

    humanity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _users
    -0.08
    Users
    -0.08
    াঘ
    -0.08
    Url
    -0.08
    房
    -0.08
    成交
    -0.08
    盒
    -0.07
     players
    -0.07
     attendees
    -0.07
     users
    -0.07
    POSITIVE LOGITS
     beings
    0.16
    -human
    0.13
    -orang
    0.13
    -machine
    0.12
     الإنسان
    0.12
     الإنسانية
    0.12
    -made
    0.11
     البشرية
    0.11
     البشر
    0.11
    ियत
    0.11
    Activations Density 0.037%

    No Known Activations