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. 112010
    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
     Rad
    -0.07
     ~
    -0.07
     sc
    -0.07
     SZ
    -0.07
     as
    -0.07
    /or
    -0.07
    erek
    -0.07
     Grid
    -0.07
    .Rad
    -0.07
     chilled
    -0.07
    POSITIVE LOGITS
     bride
    0.09
    학교
    0.09
     정확
    0.09
     wording
    0.08
     चिंता
    0.08
     clínica
    0.08
     bebé
    0.08
    Answered
    0.08
    Quieres
    0.08
    ว่า
    0.08
    Activations Density 0.025%

    No Known Activations