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. 56047
    Prev
    Next
    INDEX
    Explanations

    first

    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
     stare
    -0.08
     Gross
    -0.08
    putation
    -0.08
    Gross
    -0.07
    matic
    -0.07
    фт
    -0.07
    achael
    -0.07
    পূর্ণ
    -0.07
    мон
    -0.07
     Berm
    -0.07
    POSITIVE LOGITS
    -ever
    0.11
     থেকেই
    0.11
     glance
    0.10
     번째
    0.09
     વખત
    0.09
    -mentioned
    0.09
     నుం�
    0.08
    Child
    0.08
     tiên
    0.08
    以来
    0.08
    Activations Density 0.092%

    No Known Activations