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. 112241
    Prev
    Next
    INDEX
    Explanations

    medication dosage

    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
     getenv
    -0.08
    herits
    -0.08
     прежде
    -0.07
     gerçek
    -0.07
     [[]
    -0.07
     악
    -0.07
     Sell
    -0.07
     Lace
    -0.07
     unat
    -0.07
     лаб
    -0.07
    POSITIVE LOGITS
     doses
    0.10
     dosing
    0.09
     SINGLE
    0.08
    Single
    0.08
    -dose
    0.08
     giornata
    0.08
    ::::::::
    0.08
     adolescentes
    0.08
    SHORT
    0.08
     single
    0.08
    Activations Density 0.005%

    No Known Activations