© 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 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. 69649
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
     survey
    -0.07
     deliver
    -0.07
    (f
    -0.07
     ordinal
    -0.07
    ̂
    -0.07
     profiling
    -0.07
    ropped
    -0.07
     উপ
    -0.07
     sahib
    -0.07
    autoload
    -0.07
    POSITIVE LOGITS
     Eventually
    0.10
     slimming
    0.09
     eventually
    0.09
     сг
    0.09
    不断
    0.09
     перера
    0.09
     ilimit
    0.09
     clockwise
    0.09
    Eventually
    0.09
     ходе
    0.09
    Activations Density 0.024%

    No Known Activations