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. 77480
    Prev
    Next
    INDEX
    Explanations

    loan

    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
     Profit
    -0.08
     Gewinn
    -0.08
     iure
    -0.08
     Nicholas
    -0.08
     Shir
    -0.07
     Faker
    -0.07
    .clients
    -0.07
     Chong
    -0.07
    Profit
    -0.07
     Computational
    -0.07
    POSITIVE LOGITS
     puerta
    0.09
     modalities
    0.08
     गृह
    0.08
     бытов
    0.08
     vocational
    0.08
     cuffs
    0.08
     decisions
    0.08
     상품
    0.08
    机动车
    0.08
     mortgages
    0.08
    Activations Density 0.015%

    No Known Activations