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. 112084
    Prev
    Next
    INDEX
    Explanations

    say

    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
    意识
    -0.08
     πιθαν
    -0.08
     наг
    -0.08
     ದೇವ
    -0.07
    这
    -0.07
     जिन
    -0.07
     gods
    -0.07
     πλέον
    -0.07
    avlj
    -0.07
    夫
    -0.07
    POSITIVE LOGITS
     celui
    0.09
     decimal
    0.09
     celle
    0.09
     quelli
    0.08
     quello
    0.08
    :nth
    0.08
     ours
    0.07
    decimal
    0.07
    456
    0.07
     multiples
    0.07
    Activations Density 0.027%

    No Known Activations