© 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. 71012
    Prev
    Next
    INDEX
    Explanations

    resource

    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
     help
    -0.09
     व्य
    -0.08
    APIView
    -0.08
     Brent
    -0.08
     ayudar
    -0.08
    boards
    -0.07
    'aide
    -0.07
     estratégias
    -0.07
    .pag
    -0.07
     ventas
    -0.07
    POSITIVE LOGITS
     canta
    0.09
     Folder
    0.09
     folders
    0.08
     carpeta
    0.08
    目录
    0.08
    _FOLDER
    0.08
    (folder
    0.08
     yarn
    0.08
     jars
    0.07
    Folder
    0.07
    Activations Density 0.003%

    No Known Activations