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. 112919
    Prev
    Next
    INDEX
    Explanations

    educational outreach programs

    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
     itens
    -0.09
     stal
    -0.08
    ивал
    -0.08
     utensils
    -0.08
    ைத்து
    -0.08
    死人
    -0.08
    руш
    -0.08
    ковь
    -0.08
     healing
    -0.08
    _items
    -0.08
    POSITIVE LOGITS
     freshman
    0.10
     college
    0.09
     undergraduate
    0.09
     kindergarten
    0.09
     freshmen
    0.09
     Early
    0.09
     কলেজ
    0.09
     early
    0.09
    高中
    0.09
     Anfänger
    0.09
    Activations Density 0.068%

    No Known Activations