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. 111904
    Prev
    Next
    INDEX
    Explanations

    celebrity

    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
    舍
    -0.09
     Commiss
    -0.08
     spindle
    -0.08
     kingdom
    -0.08
    рава
    -0.08
     malt
    -0.08
     Kingdom
    -0.07
     Chlor
    -0.07
     ter
    -0.07
    attan
    -0.07
    POSITIVE LOGITS
    耀
    0.09
    /high
    0.08
    Celebrity
    0.08
     stature
    0.08
     accreditation
    0.08
     glamour
    0.08
     amassed
    0.08
    明星
    0.07
     Cathy
    0.07
     हासिल
    0.07
    Activations Density 0.038%

    No Known Activations