© 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. 11-RESID-POST-AA
    11. 99425
    Prev
    Next
    INDEX
    Explanations

    chill

    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
     уч
    -0.09
     pulley
    -0.08
     кр
    -0.07
    -Benz
    -0.07
     gagn
    -0.07
     капитал
    -0.07
     swell
    -0.07
     Elise
    -0.07
     CW
    -0.07
     elog
    -0.07
    POSITIVE LOGITS
     Bog
    0.08
    Sec
    0.08
    Bog
    0.08
    ท้าย
    0.07
     breeze
    0.07
    融
    0.07
    creen
    0.07
     Keb
    0.07
     vibes
    0.07
    -danger
    0.07
    Activations Density 0.003%

    No Known Activations