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. 120368
    Prev
    Next
    INDEX
    Explanations

    system

    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
     découvrez
    -0.10
    buffer
    -0.09
     découvert
    -0.09
    Découvrez
    -0.08
     Hammond
    -0.08
    先进
    -0.08
    grey
    -0.08
     Découvrez
    -0.08
     chik
    -0.08
     discover
    -0.08
    POSITIVE LOGITS
     equations
    0.09
     algebra
    0.09
     Numer
    0.08
     solved
    0.08
    -solving
    0.08
    成立
    0.08
    Solved
    0.08
     consequent
    0.07
     venn
    0.07
     imposed
    0.07
    Activations Density 0.007%

    No Known Activations