© 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. 54468
    Prev
    Next
    INDEX
    Explanations

    Islam

    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
     settlements
    -0.07
     bankers
    -0.07
     Designing
    -0.07
    Appending
    -0.07
    cal
    -0.07
     रोक
    -0.07
     hwnd
    -0.07
     verr
    -0.07
    ¢
    -0.07
    .column
    -0.07
    POSITIVE LOGITS
     подтверж
    0.09
     استعداد
    0.09
     affirmation
    0.08
     deklar
    0.08
     налич
    0.08
     ਦੁ
    0.08
    Declaration
    0.08
    ична
    0.08
     verbally
    0.08
     afirm
    0.08
    Activations Density 0.005%

    No Known Activations