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. 112048
    Prev
    Next
    INDEX
    Explanations

    Asking what user is doing

    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
     Opinions
    -0.08
     turnover
    -0.08
     فوائد
    -0.07
     finden
    -0.07
    udet
    -0.07
     foll
    -0.07
    氧
    -0.07
     assert
    -0.07
    ộn
    -0.07
    acd
    -0.07
    POSITIVE LOGITS
    You're
    0.09
     intentando
    0.09
     waarvoor
    0.08
    用途
    0.08
    trying
    0.08
    正在
    0.08
     项
    0.08
    Program
    0.08
    Prere
    0.08
     you're
    0.08
    Activations Density 0.022%

    No Known Activations