© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64140
    Prev
    Next
    INDEX
    Explanations

    medications and dosages

    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
     safeguards
    -0.08
    raud
    -0.08
    يض
    -0.08
     retra
    -0.07
    ʻe
    -0.07
    -0.07
    erce
    -0.07
    ecurities
    -0.07
     выг
    -0.07
     raakt
    -0.07
    POSITIVE LOGITS
     dosing
    0.11
     doses
    0.10
     সকালে
    0.10
     সকাল
    0.10
     morgens
    0.10
    每天
    0.10
     सुबह
    0.09
     supplementation
    0.09
    每日
    0.09
     দিনে
    0.09
    Activations Density 0.014%
    No Known Activations