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. 23-RESID-POST-AA
    6. 130742
    Prev
    Next
    INDEX
    Explanations

    say "ков" or "ку"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conceb
    -0.09
    िच
    -0.07
    ्यान
    -0.07
     contrace
    -0.07
     daug
    -0.07
    िध
    -0.07
     Cecil
    -0.07
     Cannes
    -0.07
    acs
    -0.07
     repress
    -0.07
    POSITIVE LOGITS
    ков
    0.12
    кова
    0.11
    ку
    0.10
    onation
    0.10
    ків
    0.10
    onnement
    0.09
    uição
    0.09
    kov
    0.09
    on
    0.09
    ком
    0.08
    Activations Density 0.001%

    No Known Activations