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. 65957
    Prev
    Next
    INDEX
    Explanations

    childbirth assistance

    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
    anhã
    -0.08
     Millions
    -0.07
     জানা
    -0.07
    pectral
    -0.07
     quasi
    -0.07
    usual
    -0.07
     revelation
    -0.07
    existent
    -0.07
     উল্লেখ
    -0.07
     quest
    -0.07
    POSITIVE LOGITS
     bedding
    0.09
     bathrooms
    0.09
    Massage
    0.09
     indien
    0.09
     sanitary
    0.08
     pillows
    0.08
    卫生
    0.08
     massage
    0.08
     uninsured
    0.08
     bedside
    0.08
    Activations Density 0.013%

    No Known Activations