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. 113025
    Prev
    Next
    INDEX
    Explanations

    EU

    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
     среднего
    -0.09
     underestimated
    -0.09
     Vor
    -0.08
     متوسط
    -0.08
     Cbd
    -0.08
    ました
    -0.08
    (Level
    -0.08
     تقد
    -0.07
     CFL
    -0.07
    (Read
    -0.07
    POSITIVE LOGITS
     stringent
    0.08
    否则
    0.08
     doctrina
    0.08
    .''
    0.08
    -containing
    0.08
     doctrine
    0.08
     verplicht
    0.08
    seau
    0.08
     хоть
    0.08
    PRISE
    0.07
    Activations Density 0.013%

    No Known Activations