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. 111854
    Prev
    Next
    INDEX
    Explanations

    give

    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
    梦想
    -0.08
     (?
    -0.08
     dreams
    -0.08
     vz
    -0.08
     అనే
    -0.08
    /dom
    -0.08
     വിദ്യാര്
    -0.07
     applications
    -0.07
    事务
    -0.07
    .ob
    -0.07
    POSITIVE LOGITS
     plus
    0.08
     제공합니다
    0.08
    sender
    0.08
     definitely
    0.07
    0.07
     Bijvoorbeeld
    0.07
     ton
    0.07
     هنا
    0.07
     Pitt
    0.07
     thoroughly
    0.07
    Activations Density 0.104%

    No Known Activations