© 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. 96395
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ern or -umbled"

    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
    ’elle
    -0.08
    once
    -0.08
     once
    -0.07
    ，把
    -0.07
     Once
    -0.07
    Once
    -0.07
    ider
    -0.07
    Anc
    -0.07
    Als
    -0.07
     fold
    -0.07
    POSITIVE LOGITS
     diar
    0.09
    uot
    0.08
    upha
    0.08
     সেপ্টেম্বর
    0.08
     સોશિયલ
    0.08
    ifornia
    0.08
     september
    0.08
    liq
    0.08
    ગ
    0.07
     ઉત્પાદન
    0.07
    Activations Density 0.000%

    No Known Activations