© 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. 19-RESID-POST-AA
    11. 18403
    Prev
    Next
    INDEX
    Explanations

    say "class"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    検索
    -0.09
    搜尋
    -0.09
    搜索
    -0.08
    Search
    -0.08
     Search
    -0.08
     mecanismos
    -0.08
     поис
    -0.08
    search
    -0.08
     उपाय
    -0.08
     axe
    -0.08
    POSITIVE LOGITS
     class
    0.18
     classes
    0.18
     класса
    0.18
    _class
    0.18
    _classes
    0.17
     클래스
    0.17
    -class
    0.16
     клас
    0.16
     classe
    0.16
    class
    0.16
    Activations Density 0.009%

    No Known Activations