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. 11755
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     Boyd
    -0.08
    irms
    -0.08
     broadcasts
    -0.08
    իկական
    -0.08
     seguem
    -0.08
     өткіз
    -0.07
     assorted
    -0.07
     Manning
    -0.07
    qty
    -0.07
     specimens
    -0.07
    POSITIVE LOGITS
     chiam
    0.08
     בשם
    0.08
     नाम
    0.08
     Alpha
    0.08
     Turbo
    0.08
     Star
    0.08
     Zot
    0.08
     name
    0.08
     GPT
    0.07
     Gaia
    0.07
    Activations Density 0.003%

    No Known Activations