© 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. 23-RESID-POST-AA
    11. 6630
    Prev
    Next
    INDEX
    Explanations

    say "May"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PCM
    -0.11
     GSM
    -0.10
     gsm
    -0.10
     QM
    -0.10
     LM
    -0.10
    _dm
    -0.10
    ZM
    -0.09
    PCM
    -0.09
    Psi
    -0.09
    lm
    -0.09
    POSITIVE LOGITS
     May
    0.46
    May
    0.45
     मई
    0.39
     মে
    0.36
     maggio
    0.35
    may
    0.34
     maio
    0.33
    -May
    0.33
     مايو
    0.33
     MAY
    0.32
    Activations Density 0.060%

    No Known Activations