© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 103268
    Prev
    Next
    INDEX
    Explanations

    say "next"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     françaises
    -0.08
     takich
    -0.07
    大量
    -0.07
     מאות
    -0.07
     מיוח
    -0.07
     longues
    -0.07
     nombreuses
    -0.07
    χετε
    -0.07
     spezielle
    -0.07
     assorted
    -0.07
    POSITIVE LOGITS
     next
    0.56
    _next
    0.53
    next
    0.52
    	next
    0.51
     अगले
    0.50
     આગામી
    0.50
     nästa
    0.50
    (next
    0.49
    .next
    0.48
     næste
    0.48
    Activations Density 0.180%

    No Known Activations