© 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. 11-RESID-POST-AA
    11. 68831
    Prev
    Next
    INDEX
    Explanations

    checkerboard squares calculation

    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
     vows
    -0.08
    unciation
    -0.08
    viado
    -0.08
    ruptcy
    -0.08
    ída
    -0.08
    {\
    -0.08
     preach
    -0.08
     bæ
    -0.08
    -0.08
     baggage
    -0.07
    POSITIVE LOGITS
     நகர
    0.09
     rectangular
    0.08
     Weihnachts
    0.08
     למצוא
    0.08
     perimeter
    0.07
    онар
    0.07
    全年
    0.07
     বস
    0.07
    ubic
    0.07
     totaled
    0.07
    Activations Density 0.019%
    No Known Activations