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

    Neuronpedia

    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. 25010
    Prev
    Next
    INDEX
    Explanations

    medications

    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
     dias
    -0.07
    524
    -0.07
     decentral
    -0.07
    dias
    -0.07
    <Vector
    -0.07
     concluded
    -0.07
    Dias
    -0.07
    .cent
    -0.07
     செ
    -0.07
     गो
    -0.07
    POSITIVE LOGITS
     lept
    0.09
     Documento
    0.08
     potassium
    0.08
     Bill
    0.08
    _bill
    0.08
     chloride
    0.08
    اپ
    0.08
    ائمة
    0.07
     Forder
    0.07
    úč
    0.07
    Activations Density 0.001%

    No Known Activations