© 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. 110605
    Prev
    Next
    INDEX
    Explanations

    polynomial

    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
     police
    -0.08
     parquet
    -0.07
    ──
    -0.07
    �
    -0.07
    /example
    -0.07
     muted
    -0.07
    _app
    -0.07
     잡
    -0.07
    pic
    -0.07
    box
    -0.07
    POSITIVE LOGITS
    elọpọ
    0.10
     apẹrẹ
    0.09
     suunn
    0.09
     adored
    0.08
    իշ
    0.08
    ਾਮ
    0.08
    ્વ
    0.08
     groe
    0.08
    સ
    0.08
     retailers
    0.08
    Activations Density 0.021%

    No Known Activations