Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44960
    Prev
    Next
    INDEX
    Explanations

    line

    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
     ارت
    -0.09
     تقدم
    -0.08
     ethic
    -0.08
     Blogging
    -0.08
     Enjoy
    -0.07
    émy
    -0.07
    éh
    -0.07
    享
    -0.07
    荐
    -0.07
    สิ
    -0.07
    POSITIVE LOGITS
     lautet
    0.11
     equations
    0.10
     समी
    0.08
     equation
    0.08
     letra
    0.08
     SAN
    0.08
    Equation
    0.08
     mathemat
    0.08
     ecu
    0.08
    0.07
    Activations Density 0.033%

    No Known Activations