Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12995
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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
    -0.09
     Or
    -0.08
    Or
    -0.08
     Inform
    -0.08
    -end
    -0.08
     Coordin
    -0.07
     Transaction
    -0.07
    पूर
    -0.07
    Deque
    -0.07
    (sys
    -0.07
    POSITIVE LOGITS
     azonban
    0.09
     negativity
    0.09
    çou
    0.09
    isz
    0.09
     negativo
    0.08
    悪
    0.08
     eint
    0.08
    irty
    0.08
    атор
    0.08
    irts
    0.08
    Activations Density 0.070%

    No Known Activations