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. 76061
    Prev
    Next
    INDEX
    Explanations

    Alternatively

    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
     sprake
    -0.08
     Severe
    -0.08
    意味着
    -0.07
     Vert
    -0.07
     aquello
    -0.07
     fonctionnalités
    -0.07
     ilişkin
    -0.07
     suhte
    -0.07
     отношении
    -0.07
    Bedroom
    -0.07
    POSITIVE LOGITS
     circumvent
    0.11
     elegantly
    0.10
     rigorous
    0.09
     steps
    0.09
     доказ
    0.08
     explanation
    0.08
     neatly
    0.08
    .nb
    0.08
    Explain
    0.08
    omatic
    0.08
    Activations Density 0.066%

    No Known Activations