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. 49089
    Prev
    Next
    INDEX
    Explanations

    包

    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
     изменений
    -0.08
    әк
    -0.08
     brû
    -0.07
     нан
    -0.07
    篮
    -0.07
    285
    -0.07
    375
    -0.07
     unveiled
    -0.07
     часов
    -0.07
     unders
    -0.07
    POSITIVE LOGITS
    posa
    0.09
    Cisco
    0.08
    Pct
    0.08
    ibble
    0.08
     Shimano
    0.08
    Garage
    0.08
    百分
    0.08
    rim
    0.07
    .And
    0.07
    Roger
    0.07
    Activations Density 0.001%

    No Known Activations