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. 120244
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     neighbor
    -0.08
     rendez
    -0.08
     Neighbor
    -0.07
     RR
    -0.07
     Galileo
    -0.07
     RAM
    -0.07
    ,String
    -0.07
     adelant
    -0.07
    /o
    -0.07
     routing
    -0.07
    POSITIVE LOGITS
    ിക്കുന്നത്
    0.09
    Destroy
    0.09
     auster
    0.09
     desconto
    0.08
    ითი
    0.08
    ორმ
    0.08
     caafima
    0.08
     രാഷ്ട്രീയ
    0.08
     สูตร
    0.08
     രാഷ്ട്രീ
    0.08
    Activations Density 0.005%

    No Known Activations