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. 88239
    Prev
    Next
    INDEX
    Explanations

    km

    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
     Vom
    -0.07
     chwil
    -0.07
    ta
    -0.07
    WAR
    -0.07
     shr
    -0.07
     null
    -0.07
    erm
    -0.07
     leek
    -0.07
    Western
    -0.07
     chirurg
    -0.07
    POSITIVE LOGITS
    氏
    0.08
    elling
    0.08
     ago
    0.08
     urma
    0.07
    .Foundation
    0.07
    _AM
    0.07
    }-{
    0.07
    ืน
    0.07
     теле
    0.07
     Horton
    0.07
    Activations Density 0.046%

    No Known Activations