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. 120347
    Prev
    Next
    INDEX
    Explanations

    errors

    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
    _buy
    -0.08
     Weih
    -0.08
    .jsdelivr
    -0.08
     Bal
    -0.08
     Libre
    -0.08
     Californ
    -0.08
     बाल
    -0.08
     Glide
    -0.08
     каль
    -0.08
     привык
    -0.07
    POSITIVE LOGITS
    Throwable
    0.12
     Throwable
    0.10
    >Error
    0.09
    entropy
    0.09
    .Exception
    0.09
     failures
    0.08
     গুরু
    0.08
    fatal
    0.08
    severity
    0.08
    Unhandled
    0.08
    Activations Density 0.002%

    No Known Activations