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. 90994
    Prev
    Next
    INDEX
    Explanations

    Java code

    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
    .css
    -0.08
    .CSS
    -0.08
    中文字
    -0.08
    ,如果
    -0.08
    .Set
    -0.08
    :"
    -0.08
    куля
    -0.08
    中国特色
    -0.08
     objectives
    -0.08
    安卓
    -0.07
    POSITIVE LOGITS
     rescue
    0.08
     Bankruptcy
    0.08
     Passenger
    0.08
     Rescue
    0.08
     Rabbit
    0.08
     Roulette
    0.08
     bankruptcy
    0.07
     Pupp
    0.07
    367
    0.07
     debugging
    0.07
    Activations Density 0.001%

    No Known Activations