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. 343
    Prev
    Next
    INDEX
    Explanations

    manual

    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
    eg
    -0.08
    -gener
    -0.08
    Nan
    -0.08
    amenti
    -0.08
    يمان
    -0.08
    _TIMESTAMP
    -0.07
    كي
    -0.07
    amento
    -0.07
    emist
    -0.07
    arium
    -0.07
    POSITIVE LOGITS
     ಸ್ಥಾನ
    0.09
     влад
    0.08
     пози
    0.08
     alley
    0.08
     інтэр
    0.08
    ભાવ
    0.08
     exhilarating
    0.08
     FOX
    0.08
     beck
    0.07
     alma
    0.07
    Activations Density 0.004%

    No Known Activations