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. 49619
    Prev
    Next
    INDEX
    Explanations

    personal opinions

    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
    parable
    -0.08
    Foundation
    -0.07
    Adaptor
    -0.07
     guía
    -0.07
    阶
    -0.07
    rollable
    -0.07
     Macintosh
    -0.07
     Dyn
    -0.07
     sin
    -0.07
     آزاد
    -0.07
    POSITIVE LOGITS
    чун
    0.09
     submissions
    0.09
     제출
    0.08
     conversations
    0.08
     의견
    0.08
     hlas
    0.08
     occurring
    0.08
     positives
    0.08
    },{
    0.08
    ),(
    0.08
    Activations Density 0.137%

    No Known Activations