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. 13008
    Prev
    Next
    INDEX
    Explanations

    in

    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
    声
    -0.08
     Wirkung
    -0.07
     verander
    -0.07
    当に
    -0.07
    很好
    -0.07
     behavior
    -0.07
     infancy
    -0.06
     verbessert
    -0.06
    -0.06
     bewe
    -0.06
    POSITIVE LOGITS
     brook
    0.08
     εργα
    0.08
     మంది
    0.08
     Raya
    0.08
     çalışan
    0.08
    cher
    0.08
    Starts
    0.07
    ierta
    0.07
     لقاء
    0.07
    starter
    0.07
    Activations Density 0.038%

    No Known Activations