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. 112996
    Prev
    Next
    INDEX
    Explanations

    complex number conjugates

    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
    <?>
    -0.09
     usted
    -0.08
     ವ
    -0.08
     Ramos
    -0.08
    립
    -0.07
     houver
    -0.07
     classified
    -0.07
     ډ
    -0.07
     vă
    -0.07
     proud
    -0.07
    POSITIVE LOGITS
     préserver
    0.09
     removes
    0.08
     Ус
    0.08
     soaked
    0.08
     Preserve
    0.08
     그대로
    0.08
     coch
    0.08
     conjug
    0.08
     preserve
    0.08
     preserves
    0.08
    Activations Density 0.056%

    No Known Activations