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. 76548
    Prev
    Next
    INDEX
    Explanations

    bracket

    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
     desen
    -0.08
    gleichen
    -0.08
     PEG
    -0.08
     fallout
    -0.07
    kten
    -0.07
     rese
    -0.07
     κά
    -0.07
    558
    -0.07
     ๆ
    -0.07
     الكامل
    -0.07
    POSITIVE LOGITS
     bany
    0.09
     Rolex
    0.08
    _perf
    0.08
     Citrus
    0.08
     invokes
    0.08
     vir
    0.08
     Retrieves
    0.08
    angent
    0.08
     hygiene
    0.07
    -ẹrọ
    0.07
    Activations Density 0.001%

    No Known Activations