© 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. 21048
    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
     algumas
    -0.10
     некоторых
    -0.09
     algunas
    -0.09
     někter
    -0.09
     nisu
    -0.09
     quelques
    -0.09
     bazı
    -0.08
    某
    -0.08
     algunos
    -0.08
     ня
    -0.08
    POSITIVE LOGITS
     demandes
    0.09
     पनि
    0.08
     նաև
    0.08
     eisini
    0.08
     պահանջ
    0.08
     έκανε
    0.08
     κάνουν
    0.08
    ,column
    0.08
     líka
    0.07
     calculations
    0.07
    Activations Density 0.000%

    No Known Activations