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. 58643
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ぁ
    -0.09
     (?)
    -0.08
     weekday
    -0.08
     predecessor
    -0.08
    lename
    -0.07
     তাহলে
    -0.07
     төл
    -0.07
    payer
    -0.07
     wtedy
    -0.07
     Northampton
    -0.07
    POSITIVE LOGITS
     countless
    0.10
     verwerkt
    0.08
    军事
    0.08
     kult
    0.07
     military
    0.07
     различных
    0.07
     militaire
    0.07
     культуры
    0.07
     abound
    0.07
     случаях
    0.07
    Activations Density 0.049%

    No Known Activations