© 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. 23-RESID-POST-AA
    11. 50801
    Prev
    Next
    INDEX
    Explanations

    say [number 109]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     механизм
    -0.08
    机制
    -0.08
     наличие
    -0.08
    apellido
    -0.08
    猪
    -0.07
     mechanism
    -0.07
    ækker
    -0.07
     mécan
    -0.07
     subtitle
    -0.07
    -esque
    -0.07
    POSITIVE LOGITS
    ині
    0.08
    .Decode
    0.08
    occi
    0.08
     comprende
    0.08
     Understanding
    0.08
    OUND
    0.07
    ोड
    0.07
    olino
    0.07
    нор
    0.07
    егов
    0.07
    Activations Density 0.044%

    No Known Activations