© 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. 110510
    Prev
    Next
    INDEX
    Explanations

    catalysts and chemical reactions

    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
     эк
    -0.08
     establecer
    -0.08
     tt
    -0.08
     clá
    -0.08
     avenue
    -0.08
    chimp
    -0.07
     variant
    -0.07
     baseada
    -0.07
     exponentially
    -0.07
     etmək
    -0.07
    POSITIVE LOGITS
     incapable
    0.09
     substances
    0.09
     inorganic
    0.09
    _ptr
    0.09
     catalyst
    0.08
    _removed
    0.08
     faults
    0.08
     unchanged
    0.08
     phẩm
    0.08
     вещества
    0.08
    Activations Density 0.004%

    No Known Activations