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. 111989
    Prev
    Next
    INDEX
    Explanations

    Caught up in events

    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
    394
    -0.07
    bie
    -0.07
     scout
    -0.07
     layout
    -0.07
    ਾਹ
    -0.07
     chess
    -0.07
    lig
    -0.07
     Pac
    -0.07
    যোগ্য
    -0.07
     vide
    -0.07
    POSITIVE LOGITS
     asuntos
    0.09
     City's
    0.09
    Caught
    0.09
     thunderstorms
    0.08
    纷
    0.08
    woo
    0.08
     políticos
    0.08
     unleashed
    0.08
     Belediyesi
    0.08
     корруп
    0.08
    Activations Density 0.013%

    No Known Activations