© 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. 51426
    Prev
    Next
    INDEX
    Explanations

    French Enlightenment

    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
     пах
    -0.08
    ="#"
    -0.08
    /fw
    -0.08
    (^
    -0.08
    ="#"><
    -0.07
     uninstall
    -0.07
    ато
    -0.07
    instr
    -0.07
    _fw
    -0.07
     store
    -0.07
    POSITIVE LOGITS
     Babe
    0.09
     gezondheids
    0.08
     Stahl
    0.08
     economist
    0.08
     condens
    0.07
     economists
    0.07
     businessmen
    0.07
     llam
    0.07
     économiques
    0.07
     D
    0.07
    Activations Density 0.004%

    No Known Activations