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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12832
    Prev
    Next
    INDEX
    Explanations

    Phone numbers

    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
    oreo
    -0.08
     پس
    -0.08
    Después
    -0.08
     cual
    -0.08
    Mountain
    -0.08
    antwort
    -0.08
     ansiedad
    -0.07
     fuente
    -0.07
     AFTER
    -0.07
     psicológico
    -0.07
    POSITIVE LOGITS
    নী
    0.09
    ন
    0.09
     Bangladesh
    0.09
     дат
    0.09
     Bengali
    0.08
     Sø
    0.08
     Denmark
    0.08
    না
    0.08
     filoz
    0.08
    gaard
    0.08
    Activations Density 0.035%

    No Known Activations