© 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. 20448
    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
     dây
    -0.10
     हथ
    -0.09
     زا
    -0.09
     trận
    -0.09
     khi
    -0.09
     squeezing
    -0.09
     гора
    -0.08
     gemstone
    -0.08
     sword
    -0.08
     ruler
    -0.08
    POSITIVE LOGITS
     যারা
    0.15
     degenen
    0.14
     cohorts
    0.13
     cohort
    0.13
     immigrants
    0.13
     जिन्होंने
    0.12
     الذين
    0.12
     individuals
    0.12
    Retention
    0.12
     ehemalige
    0.12
    Activations Density 0.010%

    No Known Activations