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. 15-RESID-POST-AA
    6. 19448
    Prev
    Next
    INDEX
    Explanations

    say "sub" or "tables"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mediocre
    -0.08
    insp
    -0.08
     purported
    -0.07
     notorious
    -0.07
     famed
    -0.07
    売
    -0.07
     alleged
    -0.07
     mà
    -0.07
    합
    -0.07
     thermique
    -0.07
    POSITIVE LOGITS
     bullet
    0.14
     paragraphs
    0.11
     Bullet
    0.11
     bullets
    0.10
     gärna
    0.10
     sentences
    0.09
     أو
    0.09
     یا
    0.09
     storytelling
    0.09
     concise
    0.09
    Activations Density 0.012%

    No Known Activations