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. 12928
    Prev
    Next
    INDEX
    Explanations

    Punctuation, 'for'

    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
     ছ
    -0.09
     ДО
    -0.08
    nir
    -0.08
     guer
    -0.08
     Rebels
    -0.08
     PRIMARY
    -0.08
    שות
    -0.07
     Guer
    -0.07
     geschützt
    -0.07
     concret
    -0.07
    POSITIVE LOGITS
     alleged
    0.09
     xử
    0.09
     mish
    0.08
     allegedly
    0.08
     mascot
    0.08
     parfois
    0.08
     raising
    0.08
     controversial
    0.08
     Omar
    0.07
     lịch
    0.07
    Activations Density 0.056%

    No Known Activations