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. 102863
    Prev
    Next
    INDEX
    Explanations

    miscellaneous items

    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
     waiver
    -0.07
     suppose
    -0.07
     disregard
    -0.07
    Alexander
    -0.07
     headphone
    -0.07
    -0.07
     skip
    -0.07
     kūpono
    -0.07
     restful
    -0.07
    ilip
    -0.07
    POSITIVE LOGITS
     Ih
    0.08
     мороз
    0.07
     Tint
    0.07
     Viz
    0.07
     Tosh
    0.07
     Martínez
    0.07
    massa
    0.07
     noirs
    0.07
     李
    0.07
     Os
    0.07
    Activations Density 1.069%

    No Known Activations