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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19310
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    robot
    -0.08
     Dover
    -0.08
    rota
    -0.08
     volunt
    -0.08
     Samurai
    -0.07
     sailors
    -0.07
     antise
    -0.07
     robots
    -0.07
     Rpc
    -0.07
     Pere
    -0.07
    POSITIVE LOGITS
    드시
    0.09
     MART
    0.09
     Dietary
    0.09
     création
    0.09
     Calories
    0.08
     постро
    0.08
     შექმ
    0.08
     dietary
    0.08
     inkomsten
    0.08
     calories
    0.08
    Activations Density 0.003%

    No Known Activations