© 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. 24918
    Prev
    Next
    INDEX
    Explanations

    Anki flashcards

    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
     hustle
    -0.09
    定位
    -0.08
     positioning
    -0.08
     motorists
    -0.07
     seques
    -0.07
     बिग
    -0.07
    ]+\
    -0.07
     سرو
    -0.07
    暖
    -0.07
     integral
    -0.07
    POSITIVE LOGITS
    ्कुल
    0.09
     caballo
    0.08
     hoogste
    0.08
     compagnon
    0.08
    horse
    0.08
     Lern
    0.08
     имеет
    0.08
     follicles
    0.08
     item's
    0.08
     карточ
    0.08
    Activations Density 0.002%

    No Known Activations