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. 19197
    Prev
    Next
    INDEX
    Explanations

    requests

    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
     same
    -0.10
     +
    -0.10
    ^
    -0.09
     due
    -0.09
     other
    -0.09
     etc
    -0.09
    1
    -0.09
     vs
    -0.09
     cos
    -0.09
     ->
    -0.08
    POSITIVE LOGITS
    してください
    0.15
    お願いします
    0.15
     করুন
    0.13
    お願
    0.13
     करें
    0.12
    Please
    0.12
     пожалуйста
    0.12
     করবেন
    0.12
     deberán
    0.12
     deverão
    0.12
    Activations Density 0.014%

    No Known Activations