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. 43239
    Prev
    Next
    INDEX
    Explanations

    white elephant gift exchanges

    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
     horizons
    -0.09
    )V
    -0.08
    Grâce
    -0.08
     درجات
    -0.08
    \Api
    -0.07
     Grâce
    -0.07
    天气
    -0.07
    -native
    -0.07
    足
    -0.07
     Lily
    -0.07
    POSITIVE LOGITS
    rod
    0.09
     izl
    0.08
     wyp
    0.08
     bä
    0.08
    ంజ
    0.08
    iliz
    0.08
     dön
    0.08
     schad
    0.08
    BW
    0.08
     dönüş
    0.07
    Activations Density 0.001%

    No Known Activations