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. 19494
    Prev
    Next
    INDEX
    Explanations

    layout

    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
     geïnteresseerd
    -0.08
    THON
    -0.08
     Rebels
    -0.08
    机器人
    -0.08
    注册码
    -0.07
     headaches
    -0.07
     friendships
    -0.07
     vieille
    -0.07
     আত
    -0.07
    骗局
    -0.07
    POSITIVE LOGITS
    -width
    0.09
    width
    0.09
     largura
    0.08
     adapter
    0.08
    _width
    0.08
    izam
    0.07
     પહ
    0.07
    while
    0.07
    Width
    0.07
    -thumbnail
    0.07
    Activations Density 0.001%

    No Known Activations