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. 65229
    Prev
    Next
    INDEX
    Explanations

    isp

    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
    366
    -0.09
    nutrition
    -0.08
    Inf
    -0.08
     nostrum
    -0.08
     Nutrition
    -0.08
     infantry
    -0.08
    Nutrition
    -0.07
    rust
    -0.07
     domain
    -0.07
    430
    -0.07
    POSITIVE LOGITS
     특징
    0.08
     वैश
    0.08
     trenutno
    0.08
    特色
    0.08
    .Det
    0.08
     medarbe
    0.07
     goofy
    0.07
    员工
    0.07
     employés
    0.07
     कर्मचार
    0.07
    Activations Density 0.002%

    No Known Activations