© 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. 111003
    Prev
    Next
    INDEX
    Explanations

    , or

    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
    wiąz
    -0.09
     synthetic
    -0.07
    -0.07
    是不是
    -0.07
    iray
    -0.07
    ibraries
    -0.07
     interaction
    -0.07
     fratern
    -0.07
     Beaumont
    -0.07
    怎么看
    -0.07
    POSITIVE LOGITS
     whichever
    0.12
    任选
    0.09
     Feel
    0.09
     sel
    0.09
    Sel
    0.08
     comfortably
    0.08
     Pick
    0.08
     lainnya
    0.08
     cualquiera
    0.08
    ก็
    0.08
    Activations Density 0.056%
    No Known Activations