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. 12115
    Prev
    Next
    INDEX
    Explanations

    influences

    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
     synonymous
    -0.08
    .psi
    -0.08
    issuer
    -0.08
    OUGH
    -0.08
     affiliated
    -0.07
     Oui
    -0.07
     Robertson
    -0.07
     patriotic
    -0.07
    #pragma
    -0.07
    ingredient
    -0.07
    POSITIVE LOGITS
    zụ
    0.09
     vice
    0.09
    0.09
     wiederum
    0.09
    باد
    0.08
     versa
    0.08
    zm
    0.08
    án
    0.08
     An
    0.08
     Janu
    0.07
    Activations Density 0.023%

    No Known Activations