© 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. 70333
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    .tem
    -0.07
    roller
    -0.07
     abordagem
    -0.07
    uld
    -0.07
    .tm
    -0.07
    heur
    -0.07
     நல்ல
    -0.07
    minimum
    -0.07
     nou
    -0.07
    excel
    -0.07
    POSITIVE LOGITS
     Hart
    0.08
     打
    0.08
    <a
    0.08
    Hart
    0.07
     році
    0.07
     కాగా
    0.07
    FFFFFFFF
    0.07
     году
    0.07
    accessible
    0.07
    568
    0.07
    Activations Density 0.148%

    No Known Activations