Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 88302
    Prev
    Next
    INDEX
    Explanations

    using

    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
     kisim
    -0.08
     праг
    -0.08
     രാഷ്ട്രീയ
    -0.08
     sympathetic
    -0.08
     prince
    -0.08
     quello
    -0.07
     narciss
    -0.07
    Ime
    -0.07
     Mona
    -0.07
    .'"
    -0.07
    POSITIVE LOGITS
    -description
    0.09
    description
    0.09
    	description
    0.09
    描述
    0.09
     description
    0.09
    _description
    0.09
     descriptions
    0.09
     exposures
    0.08
     Description
    0.08
     descriptors
    0.08
    Activations Density 0.000%

    No Known Activations