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. 11-RESID-POST-AA
    6. 46806
    Prev
    Next
    INDEX
    Explanations

    heap data structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     werkelijkheid
    -0.08
    ண்டும்
    -0.08
    _symbols
    -0.08
     conduit
    -0.08
    ër
    -0.08
     boob
    -0.08
     comprob
    -0.08
    activex
    -0.07
     alsnog
    -0.07
    scheduled
    -0.07
    POSITIVE LOGITS
    uct
    0.08
     والتعليم
    0.08
     dam
    0.07
     Hillary
    0.07
     очищ
    0.07
     máxima
    0.07
     priority
    0.07
     whitening
    0.07
     Read
    0.07
    ikho
    0.07
    Activations Density 0.001%

    No Known Activations