© 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. 110806
    Prev
    Next
    INDEX
    Explanations

    sensor

    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
     zás
    -0.09
     dele
    -0.08
     Venez
    -0.08
     insulating
    -0.07
     نوی
    -0.07
     Moss
    -0.07
     Cabinet
    -0.07
     космет
    -0.07
    896
    -0.07
     besk
    -0.07
    POSITIVE LOGITS
    -equipped
    0.08
     partic
    0.08
    -enabled
    0.08
     Turbo
    0.08
     pus
    0.08
     schlech
    0.08
    生命
    0.08
    ial
    0.07
     pups
    0.07
     장
    0.07
    Activations Density 0.008%

    No Known Activations