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. 131065
    Prev
    Next
    INDEX
    Explanations

    102

    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
    ul
    -0.07
     wichtiger
    -0.07
    berg
    -0.07
     trang
    -0.07
    toe
    -0.07
    &page
    -0.07
    capital
    -0.07
    alp
    -0.07
    alz
    -0.07
    lå
    -0.07
    POSITIVE LOGITS
     сантим
    0.08
    ынам
    0.08
     heti
    0.08
    کې
    0.08
     Cannon
    0.08
     يرج
    0.08
    ындагы
    0.08
     Inspir
    0.08
     эффект
    0.08
    зіць
    0.07
    Activations Density 0.001%

    No Known Activations