© 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. 44334
    Prev
    Next
    INDEX
    Explanations

    saturation and chinese

    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
    主人
    -0.09
     Joan
    -0.08
    شروع
    -0.08
    inspection
    -0.08
    *object
    -0.07
     dự
    -0.07
     kê
    -0.07
    .clone
    -0.07
     Biblia
    -0.07
    ollow
    -0.07
    POSITIVE LOGITS
     Todd
    0.08
    Todd
    0.08
     Trent
    0.07
    中文字
    0.07
     trance
    0.07
     Kuma
    0.07
     Nie
    0.07
     Traverse
    0.07
    不了
    0.07
     થયા
    0.07
    Activations Density 0.002%

    No Known Activations