© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 45684
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ેણ
    -0.08
     ముఖ
    -0.08
    |)↵
    -0.08
     Vij
    -0.07
     یعنی
    -0.07
    ারের
    -0.07
    ص
    -0.07
    ాలని
    -0.07
     FACE
    -0.07
     ارسال
    -0.07
    POSITIVE LOGITS
    _rom
    0.08
    超过
    0.08
    tray
    0.08
     proc
    0.08
    proc
    0.08
    jem
    0.08
    minor
    0.07
     Prelude
    0.07
     начина
    0.07
    frica
    0.07
    Activations Density 0.003%

    No Known Activations