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. 112152
    Prev
    Next
    INDEX
    Explanations

    origins and residence

    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
    _material
    -0.08
     thrott
    -0.08
    /rest
    -0.08
     corners
    -0.07
    /grid
    -0.07
    /dialog
    -0.07
    _feedback
    -0.07
    /material
    -0.07
    .iterator
    -0.07
    /footer
    -0.07
    POSITIVE LOGITS
     assimilation
    0.09
     multinational
    0.09
     residence
    0.09
     Hispanic
    0.09
     hybr
    0.08
     assimil
    0.08
     hybride
    0.08
     immigrant
    0.08
     Residence
    0.08
     immersed
    0.08
    Activations Density 0.093%

    No Known Activations