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. 15-RESID-POST-AA
    6. 19361
    Prev
    Next
    INDEX
    Explanations

    fruit of the spirit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    찬
    -0.08
    I'm
    -0.08
    ’s
    -0.07
    Sharp
    -0.07
    Status
    -0.07
    II
    -0.07
     perspectives
    -0.07
    Force
    -0.07
    Line
    -0.07
    _should
    -0.07
    POSITIVE LOGITS
     Spazier
    0.08
     isikhathi
    0.08
     serializer
    0.08
    ратите
    0.08
     jardín
    0.08
     fruto
    0.08
     Produktion
    0.08
     produzir
    0.08
     işlet
    0.08
    ремя
    0.07
    Activations Density 0.001%

    No Known Activations