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. 78637
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
     representation
    -0.08
    waju
    -0.08
     microw
    -0.08
    y's
    -0.08
     beauty
    -0.07
    Pete
    -0.07
     quote
    -0.07
     Yuk
    -0.07
     encl
    -0.07
     Olymp
    -0.07
    POSITIVE LOGITS
     которого
    0.10
    ={{
    0.09
    तम
    0.08
     <<"
    0.08
     RS
    0.08
    ="
    0.08
    <double
    0.08
     Raj
    0.07
     ?,
    0.07
     Arial
    0.07
    Activations Density 0.054%

    No Known Activations