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. 112950
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ויב
    -0.08
    .subtitle
    -0.08
     uburyo
    -0.08
    .is
    -0.07
    .includes
    -0.07
     hopped
    -0.07
     camper
    -0.07
     maquiagem
    -0.07
    .allowed
    -0.07
    .oauth
    -0.07
    POSITIVE LOGITS
     imminent
    0.08
    Dass
    0.08
     eint
    0.07
     vocational
    0.07
     અકસ્માત
    0.07
    uffle
    0.07
     légumes
    0.07
     thất
    0.07
     Theft
    0.07
     pošk
    0.07
    Activations Density 0.004%

    No Known Activations