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. 52963
    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
     موضوع
    -0.08
     sauf
    -0.08
    اط
    -0.08
    ?>
    ↵
    -0.08
     طرف
    -0.08
     معرفة
    -0.07
     ثق
    -0.07
    ುತ್ತಿದೆ
    -0.07
     वैश
    -0.07
    ouver
    -0.07
    POSITIVE LOGITS
    -ng
    0.08
    uffed
    0.07
     швид
    0.07
     संकट
    0.07
    uel
    0.07
    ,Q
    0.07
    chr
    0.07
    ,and
    0.07
    big
    0.07
    uschen
    0.07
    Activations Density 0.010%

    No Known Activations