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. 58525
    Prev
    Next
    INDEX
    Explanations

    participant

    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
     apie
    -0.09
     når
    -0.08
     налич
    -0.08
    iamiento
    -0.08
    jerë
    -0.08
     seconda
    -0.08
     ihtiyaç
    -0.08
     QSize
    -0.08
     जर
    -0.08
     dentes
    -0.08
    POSITIVE LOGITS
    hip
    0.08
    prent
    0.08
     living
    0.08
     residence
    0.08
     Living
    0.07
    нич
    0.07
     Nig
    0.07
    生活
    0.07
     Ash
    0.07
    habit
    0.07
    Activations Density 0.003%

    No Known Activations