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. 12109
    Prev
    Next
    INDEX
    Explanations

    ub/scrub

    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
     wys
    -0.08
    isen
    -0.07
    ooling
    -0.07
    /time
    -0.07
    aler
    -0.07
    (es
    -0.07
     documenting
    -0.07
    ensas
    -0.07
     Lar
    -0.07
    .problem
    -0.07
    POSITIVE LOGITS
    ದಿ
    0.09
    ργάν
    0.08
    毕业
    0.08
    тың
    0.08
    ಿಂದ
    0.08
     Kör
    0.08
    วม
    0.08
    ದಲ್ಲಿ
    0.08
    јед
    0.08
     �
    0.08
    Activations Density 0.002%

    No Known Activations