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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111326
    Prev
    Next
    INDEX
    Explanations

    add

    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
     stij
    -0.07
    荣耀
    -0.07
     pust
    -0.07
     extr
    -0.07
    skins
    -0.07
     nostalgia
    -0.07
     league
    -0.07
     imposto
    -0.07
    EO
    -0.07
    σκ
    -0.07
    POSITIVE LOGITS
     PDE
    0.10
    Ges
    0.08
     кое
    0.08
     коом
    0.08
     wodurch
    0.08
    -write
    0.08
     депут
    0.07
     ensuing
    0.07
     defnydd
    0.07
    fügb
    0.07
    Activations Density 0.003%

    No Known Activations