© 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. 43517
    Prev
    Next
    INDEX
    Explanations

    as/виде

    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
     나는
    -0.08
    why
    -0.08
    settings
    -0.08
    rometer
    -0.07
    Logic
    -0.07
     meanwhile
    -0.07
    나는
    -0.07
     impart
    -0.07
    stackoverflow
    -0.07
    법
    -0.07
    POSITIVE LOGITS
     separate
    0.09
     самостоятель
    0.09
     связано
    0.09
     offene
    0.09
     полноцен
    0.09
     еди
    0.09
     AGM
    0.08
     Teil
    0.08
    合集
    0.08
     Mittelpunkt
    0.08
    Activations Density 0.052%

    No Known Activations