© 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. 23-RESID-POST-AA
    11. 51430
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trend
    -0.11
    :event
    -0.10
    Funcs
    -0.10
    movement
    -0.09
    constraint
    -0.09
    Temps
    -0.09
    :item
    -0.09
     Contractors
    -0.09
     Entrepreneurs
    -0.09
     Relig
    -0.09
    POSITIVE LOGITS
     fewer
    0.15
     total
    0.15
    개의
    0.14
     वटा
    0.14
     dozen
    0.14
     thousand
    0.13
     kilograms
    0.13
     additional
    0.13
     million
    0.13
    %
    0.12
    Activations Density 0.120%

    No Known Activations