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. 29818
    Prev
    Next
    INDEX
    Explanations

    r

    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
    \Active
    -0.09
     зем
    -0.08
     неожидан
    -0.08
     Goldman
    -0.08
    =Integer
    -0.07
    że
    -0.07
    ាក់
    -0.07
    223
    -0.07
     Sarat
    -0.07
     PLUS
    -0.07
    POSITIVE LOGITS
     segundos
    0.08
    出台
    0.08
    اذ
    0.08
     runs
    0.07
     extractor
    0.07
    رفة
    0.07
     silloin
    0.07
     extraction
    0.07
     toho
    0.07
     eje
    0.07
    Activations Density 0.003%

    No Known Activations