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. 12833
    Prev
    Next
    INDEX
    Explanations

    Avoiding/preventing (code context)

    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
    ('='
    -0.08
    ('/')↵
    -0.08
     '/'↵
    -0.08
     concent
    -0.08
     Folgen
    -0.08
     ورک
    -0.08
     stammen
    -0.07
     Hana
    -0.07
    opor
    -0.07
     مطابق
    -0.07
    POSITIVE LOGITS
    .prevent
    0.09
    Dummy
    0.09
    ,否则
    0.09
    dummy
    0.09
    防
    0.09
     dummy
    0.09
    �
    0.08
     upkeep
    0.08
     prevents
    0.08
     puni
    0.08
    Activations Density 0.002%

    No Known Activations