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. 56102
    Prev
    Next
    INDEX
    Explanations

    colon

    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
     connaître
    -0.08
     Know
    -0.07
     generous
    -0.07
     알려
    -0.07
     brinc
    -0.07
    .rec
    -0.07
     conos
    -0.07
     જાણી
    -0.07
     أشهر
    -0.07
    於
    -0.06
    POSITIVE LOGITS
     whatsoever
    0.09
     bedragen
    0.08
    は禁止
    0.08
     anywhere
    0.08
     ниг
    0.08
     кроме
    0.08
     okenn
    0.07
     ни
    0.07
    -либо
    0.07
     کسی
    0.07
    Activations Density 0.006%

    No Known Activations