Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61171
    Prev
    Next
    INDEX
    Explanations

    code

    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
     wallpaper
    -0.08
    Cls
    -0.08
    _Work
    -0.08
    ividual
    -0.07
     فيه
    -0.07
    ’inté
    -0.07
    richtung
    -0.07
     involve
    -0.07
     ക്ഷേ
    -0.07
    Prefer
    -0.07
    POSITIVE LOGITS
     слово
    0.09
     Ев
    0.08
     mich
    0.07
     RF
    0.07
    іла
    0.07
     meat
    0.07
     рассчиты
    0.07
     combats
    0.07
     আমি
    0.07
     Tuz
    0.07
    Activations Density 0.005%

    No Known Activations