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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102323
    Prev
    Next
    INDEX
    Explanations

    News and Place names

    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
    atgeber
    -0.11
    本道
    -0.11
    uteqart
    -0.11
     ცხოვრების
    -0.11
     სიცოცხ
    -0.11
    leriniň
    -0.10
    ifukwa
    -0.10
    itsumik
    -0.10
     კეთ
    -0.10
    otlhe
    -0.10
    POSITIVE LOGITS
     Airlines
    0.11
    Football
    0.11
     Olympics
    0.11
    Crime
    0.11
     football
    0.10
    Year
    0.10
    's
    0.10
    Cars
    0.10
    Music
    0.09
    Employees
    0.09
    Activations Density 0.077%

    No Known Activations