© 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. 63257
    Prev
    Next
    INDEX
    Explanations

    laws of physics

    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
    aje
    -0.08
    نش
    -0.07
     remarks
    -0.07
    -range
    -0.07
    olive
    -0.07
    ocon
    -0.07
     تجهيز
    -0.07
    Chief
    -0.07
    irut
    -0.07
     olives
    -0.07
    POSITIVE LOGITS
     governing
    0.18
     rules
    0.18
     नियम
    0.18
     reglas
    0.17
     regras
    0.17
     règles
    0.17
    规律
    0.16
    规则
    0.16
     governs
    0.16
     govern
    0.16
    Activations Density 0.043%

    No Known Activations