© 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. 19-RESID-POST-AA
    11. 21274
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capped
    -0.09
     قريب
    -0.08
    .nano
    -0.08
     MICRO
    -0.08
     zik
    -0.08
     raibh
    -0.08
     زوج
    -0.08
    lık
    -0.07
     хват
    -0.07
     slaughter
    -0.07
    POSITIVE LOGITS
     transformations
    0.12
     transformation
    0.12
     transformación
    0.12
     modifies
    0.12
     shifts
    0.12
     transforms
    0.12
     shift
    0.11
     corresponds
    0.11
     transformar
    0.10
     bedeutet
    0.10
    Activations Density 0.008%

    No Known Activations