© 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. 51449
    Prev
    Next
    INDEX
    Explanations

    D

    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
    Carn
    -0.09
    Indirect
    -0.09
    CIA
    -0.09
    They
    -0.08
    Denied
    -0.08
    Estr
    -0.08
    Samuel
    -0.08
    ага
    -0.08
    صل
    -0.08
    Cue
    -0.08
    POSITIVE LOGITS
    iciembre
    0.10
    étails
    0.09
    923
    0.09
     entdecken
    0.09
    ựa
    0.08
    963
    0.08
    zię
    0.08
    ેક
    0.08
     REPORT
    0.08
    RAFT
    0.08
    Activations Density 0.022%

    No Known Activations