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. 77403
    Prev
    Next
    INDEX
    Explanations

    Medical help/advice

    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
     अब
    -0.08
     STO
    -0.08
     राज
    -0.08
     du
    -0.07
     graças
    -0.07
     COD
    -0.07
     dzięki
    -0.07
     शासन
    -0.07
     ثابت
    -0.07
     qul
    -0.07
    POSITIVE LOGITS
     assistance
    0.09
     urgent
    0.09
     promptly
    0.09
     urgente
    0.08
     도움
    0.08
    才能
    0.08
     urgently
    0.08
    _pose
    0.08
    Doors
    0.08
    _args
    0.08
    Activations Density 0.047%

    No Known Activations