© 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. 68783
    Prev
    Next
    INDEX
    Explanations

    math and programming

    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
    ijo
    -0.08
     tanti
    -0.08
     Hobby
    -0.07
    شان
    -0.07
    _CERT
    -0.07
     करते
    -0.07
     centímetros
    -0.07
     chit
    -0.07
    ایش
    -0.07
     जाते
    -0.07
    POSITIVE LOGITS
    分别
    0.12
     consisting
    0.09
     comprises
    0.09
     terdiri
    0.09
     یعنی
    0.09
     consisted
    0.09
     consists
    0.09
     namely
    0.09
     consist
    0.09
     الثلاث
    0.09
    Activations Density 0.077%

    No Known Activations