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. 15-RESID-POST-AA
    6. 19110
    Prev
    Next
    INDEX
    Explanations

    say "="

    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
     “
    -0.07
     ministra
    -0.07
     مه
    -0.07
     decrypted
    -0.07
     Cap
    -0.07
    situ
    -0.07
     aptly
    -0.07
     enigmatic
    -0.06
     "
    -0.06
     etm
    -0.06
    POSITIVE LOGITS
    ച്ചി
    0.10
    .Guna
    0.09
    NBC
    0.09
    ումբ
    0.09
    ССР
    0.09
     ნაწილი
    0.09
    -ის
    0.09
    ემბ
    0.09
    -ի
    0.09
    -ын
    0.09
    Activations Density 0.005%

    No Known Activations