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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 44792
    Prev
    Next
    INDEX
    Explanations

    QR

    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
    経験
    -0.10
     bills
    -0.08
     경험
    -0.08
     Habe
    -0.08
     Erfahr
    -0.08
    经历
    -0.08
     erlaub
    -0.08
    亲
    -0.08
     Governors
    -0.08
     provin
    -0.08
    POSITIVE LOGITS
    chat
    0.08
    machine
    0.08
    dots
    0.08
    ammat
    0.07
    ography
    0.07
     படம்
    0.07
    二维码
    0.07
    arith
    0.07
    ogram
    0.07
    ග
    0.07
    Activations Density 0.002%

    No Known Activations