© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7493
    Prev
    Next
    INDEX
    Explanations

    three or four

    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
    -mag
    -0.08
     Magnum
    -0.08
     Milliarden
    -0.08
    sele
    -0.07
    -python
    -0.07
    zit
    -0.07
     expect
    -0.07
    _boolean
    -0.07
     تصور
    -0.07
    ූ
    -0.07
    POSITIVE LOGITS
     найти
    0.09
     утром
    0.09
     выполнить
    0.08
     фав
    0.08
    0.08
     пер
    0.08
     культуры
    0.07
     выполнять
    0.07
     clicks
    0.07
     доп
    0.07
    Activations Density 0.003%

    No Known Activations