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. 54269
    Prev
    Next
    INDEX
    Explanations

    Medical assistant, channel analysis

    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
     എ
    -0.08
     white
    -0.08
     li
    -0.07
    :
    -0.07
    (bl
    -0.07
     ഈ
    -0.07
    (len
    -0.07
     White
    -0.07
    /text
    -0.07
     thuật
    -0.07
    POSITIVE LOGITS
     toddlers
    0.10
     Roi
    0.10
     Tā
    0.09
     Artemis
    0.08
    รีย
    0.08
     Detox
    0.08
     toddler
    0.08
    .Completed
    0.08
     tranquilo
    0.08
    慢
    0.08
    Activations Density 0.000%

    No Known Activations