© 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. 19-RESID-POST-AA
    11. 20746
    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
    न्द
    -0.09
    denes
    -0.08
    vens
    -0.08
     الدنيا
    -0.08
     contexto
    -0.08
     प्रण
    -0.08
     Indic
    -0.08
    -esque
    -0.07
    context
    -0.07
    Default
    -0.07
    POSITIVE LOGITS
     behind
    0.14
    ually
    0.13
     detrás
    0.12
    behind
    0.11
     заключается
    0.11
     وراء
    0.11
     Behind
    0.11
     verfol
    0.11
     relies
    0.11
     verfolgen
    0.11
    Activations Density 0.015%

    No Known Activations