Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112178
    Prev
    Next
    INDEX
    Explanations

    and

    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
    274
    -0.08
    966
    -0.08
     Nepal
    -0.07
    પ
    -0.07
    992
    -0.07
    411
    -0.07
    예약
    -0.07
     Packers
    -0.07
     развит
    -0.07
     개인
    -0.07
    POSITIVE LOGITS
     surroundings
    0.11
    を見る
    0.09
     scenery
    0.08
     entorno
    0.08
    :
    0.08
     खाना
    0.08
     arbete
    0.08
     kautta
    0.07
    ところ
    0.07
     händer
    0.07
    Activations Density 0.005%

    No Known Activations