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. 106334
    Prev
    Next
    INDEX
    Explanations

    standing desks

    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
     devis
    -0.08
    îtr
    -0.08
     devised
    -0.07
    猜
    -0.07
    Tin
    -0.07
     exhibited
    -0.07
    ıt
    -0.07
    ointed
    -0.07
     desconoc
    -0.07
     eminent
    -0.07
    POSITIVE LOGITS
     ergonomic
    0.12
     ergonom
    0.10
     Wellness
    0.10
     ADHD
    0.10
     sleek
    0.10
     ডেস্ক
    0.09
     Combo
    0.09
     wellness
    0.09
     الالت
    0.09
     rocker
    0.09
    Activations Density 0.012%

    No Known Activations