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. 88228
    Prev
    Next
    INDEX
    Explanations

    255

    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
    huma
    -0.08
    hair
    -0.08
    amara
    -0.08
    ibr
    -0.08
    omar
    -0.08
    ño
    -0.08
    었다
    -0.08
     nici
    -0.08
     امت
    -0.08
    raš
    -0.07
    POSITIVE LOGITS
     Bangladesh
    0.08
    обор
    0.07
     hell
    0.07
     ZIP
    0.07
     uphe
    0.07
     Cp
    0.07
    েড
    0.07
     Applic
    0.07
     Vars
    0.07
     cutoff
    0.07
    Activations Density 0.001%

    No Known Activations