© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6595
    Prev
    Next
    INDEX
    Explanations

    sides

    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
    -it
    -0.09
    (al
    -0.09
    -over
    -0.08
    -al
    -0.08
    158
    -0.08
    312
    -0.08
    -before
    -0.08
    -Al
    -0.08
     semantic
    -0.07
    Annotated
    -0.07
    POSITIVE LOGITS
     razy
    0.11
     appropriately
    0.11
     suitably
    0.11
    .expr
    0.10
     ধরে
    0.09
     sides
    0.09
     times
    0.09
     expr
    0.09
     pleasantly
    0.09
     numerator
    0.09
    Activations Density 0.020%

    No Known Activations