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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19600
    Prev
    Next
    INDEX
    Explanations

    titles and brand names

    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
    -0.09
     okre
    -0.08
    ,又
    -0.08
    ៀត
    -0.08
     muck
    -0.08
     træ
    -0.08
    筛
    -0.08
     উপজ
    -0.08
     conteú
    -0.08
     aquello
    -0.08
    POSITIVE LOGITS
     Barack
    0.08
    عديد
    0.08
     بسیاری
    0.08
     airports
    0.08
     Lord
    0.08
    Lord
    0.08
     gesamten
    0.08
    202
    0.08
     Yosemite
    0.08
     birçok
    0.08
    Activations Density 0.031%

    No Known Activations