© 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 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. 112477
    Prev
    Next
    INDEX
    Explanations

    greatest

    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
     nsh
    -0.09
    ismen
    -0.08
     beisp
    -0.08
     Thorough
    -0.08
     programm
    -0.07
     Fixture
    -0.07
     yine
    -0.07
     thorough
    -0.07
     flair
    -0.07
     né
    -0.07
    POSITIVE LOGITS
     subtle
    0.08
     permanecer
    0.08
     confiar
    0.08
     प्रतिब
    0.07
    ov
    0.07
    لمات
    0.07
    "?
    0.07
     satisfe
    0.07
     छन्
    0.07
    দান
    0.07
    Activations Density 0.036%

    No Known Activations