© 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. 103328
    Prev
    Next
    INDEX
    Explanations

    say two-digit number

    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
     öllum
    -0.10
    ၿ
    -0.09
    ာင္း
    -0.09
     masiku
    -0.09
    期开奖
    -0.09
     öðrum
    -0.09
    စ္
    -0.09
    ரவ
    -0.09
    ႀ
    -0.09
    éir
    -0.09
    POSITIVE LOGITS
    ,
    0.08
    owers
    0.07
     gelang
    0.07
     (
    0.07
     Linden
    0.06
     such
    0.06
     argument
    0.06
    place
    0.06
    apele
    0.06
    boss
    0.06
    Activations Density 0.005%

    No Known Activations