© 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. 94398
    Prev
    Next
    INDEX
    Explanations

    **

    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
     மேற்க
    -0.08
     yiy
    -0.08
    cija
    -0.08
    不断
    -0.07
    -learning
    -0.07
    ાવી
    -0.07
    .?
    -0.07
    -rounded
    -0.07
    ଦ
    -0.07
     extraction
    -0.07
    POSITIVE LOGITS
     screenplay
    0.10
    Prelude
    0.10
     premiered
    0.09
     Prelude
    0.09
     Роб
    0.09
    Saga
    0.09
    redux
    0.09
     суда
    0.08
    Compiled
    0.08
     название
    0.08
    Activations Density 0.013%

    No Known Activations