© 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. 7958
    Prev
    Next
    INDEX
    Explanations

    Crossover stories and reactions

    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
    ')}↵
    -0.08
    稿
    -0.08
    artoq
    -0.07
    stava
    -0.07
     stated
    -0.07
    ')↵↵↵
    -0.07
     Dingen
    -0.07
    çar
    -0.07
     ต่อ
    -0.07
    issima
    -0.07
    POSITIVE LOGITS
     glo
    0.08
     mil
    0.07
     والز
    0.07
     Dynamics
    0.07
     fah
    0.07
     ಹಾಗೂ
    0.07
     Мил
    0.07
     sekt
    0.07
    ыл
    0.07
    ザー
    0.07
    Activations Density 0.041%

    No Known Activations