Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 126
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    近年来
    -0.09
    倡
    -0.07
     നിരവധി
    -0.07
    年份
    -0.07
     Дав
    -0.07
    /domain
    -0.07
    ്യമ
    -0.07
    ениями
    -0.07
     };↵↵
    -0.07
    enable
    -0.07
    POSITIVE LOGITS
     destinations
    0.11
     destination
    0.11
    Destination
    0.11
    destination
    0.10
     menuju
    0.10
     reaching
    0.10
     পৌঁ
    0.10
     stopping
    0.10
     پہنچ
    0.10
     soti
    0.10
    Activations Density 0.011%

    No Known Activations