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

    Neuronpedia

    APICircuit 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. 88312
    Prev
    Next
    INDEX
    Explanations

    light

    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
     ابو
    -0.09
     זאל
    -0.09
     Pizza
    -0.09
     Motto
    -0.09
     غو
    -0.09
     thov
    -0.09
     ปลา
    -0.09
     حدیث
    -0.09
     الوزير
    -0.09
    -0.09
    POSITIVE LOGITS
    इ
    0.08
    ,
    0.08
     consolid
    0.07
     dozens
    0.07
    100
    0.07
    —
    0.07
    (const
    0.07
    24
    0.07
    unning
    0.07
    const
    0.07
    Activations Density 0.302%

    No Known Activations