© 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. 51535
    Prev
    Next
    INDEX
    Explanations

    the

    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
    GRAY
    -0.10
    _PA
    -0.09
    Gray
    -0.09
    EDIT
    -0.09
    gray
    -0.09
    STATE
    -0.09
     DRAW
    -0.09
    PLAN
    -0.09
    edit
    -0.08
     Geo
    -0.08
    POSITIVE LOGITS
     സുര
    0.11
     आब
    0.09
     suprem
    0.08
    εκ
    0.08
     otr
    0.08
     עקס
    0.08
     ეპ
    0.08
     երև
    0.08
     faucibus
    0.08
     frisch
    0.08
    Activations Density 0.007%

    No Known Activations