© 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. 69978
    Prev
    Next
    INDEX
    Explanations

    оказание

    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
    /XMLSchema
    -0.08
    最低
    -0.07
    cstring
    -0.07
    kick
    -0.07
     Angeb
    -0.07
    iou
    -0.07
     വേണ്ടി
    -0.07
    lie
    -0.07
    響
    -0.07
    節
    -0.07
    POSITIVE LOGITS
    0.07
     footing
    0.07
    raint
    0.07
     pav
    0.07
     torn
    0.07
    eyen
    0.07
     Perry
    0.07
     submet
    0.07
     OST
    0.07
    ांत
    0.07
    Activations Density 0.013%
    No Known Activations