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. 9150
    Prev
    Next
    INDEX
    Explanations

    market

    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
     biker
    -0.09
     અમ
    -0.08
    nose
    -0.08
     માર
    -0.08
    vider
    -0.07
     naw
    -0.07
    terror
    -0.07
    meric
    -0.07
    -0.07
    mares
    -0.07
    POSITIVE LOGITS
     compromis
    0.08
     volonté
    0.08
     الوضع
    0.07
     لها
    0.07
     ساز
    0.07
     forfait
    0.07
     less
    0.07
     loogu
    0.07
     Vat
    0.07
     الهدف
    0.07
    Activations Density 0.000%

    No Known Activations