© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70293
    Prev
    Next
    INDEX
    Explanations

    test

    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
     fearing
    -0.08
     ಹಿಂದ
    -0.08
     اطلاع
    -0.08
     Pen
    -0.08
     penalties
    -0.07
    zijn
    -0.07
     احتمال
    -0.07
    ល់
    -0.07
    fear
    -0.07
     استعداد
    -0.07
    POSITIVE LOGITS
    /test
    0.09
    -testing
    0.09
    测试
    0.09
    /debug
    0.09
     manually
    0.08
    .Test
    0.08
     thoroughly
    0.08
     Deployment
    0.08
    848
    0.08
    .assert
    0.08
    Activations Density 0.014%

    No Known Activations