© 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. 47705
    Prev
    Next
    INDEX
    Explanations

    say "ary" words

    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
     vrijeme
    -0.09
     yaj
    -0.09
     yav
    -0.08
     İ
    -0.08
    	y
    -0.08
     ziyaret
    -0.08
     cit
    -0.08
     waktu
    -0.08
     panahon
    -0.08
     Zlat
    -0.08
    POSITIVE LOGITS
    ат
    0.08
    ти
    0.08
    adomo
    0.08
    ers
    0.08
    eneuve
    0.08
    sg
    0.08
    desk
    0.08
    ани
    0.08
    ск
    0.08
     Desk
    0.07
    Activations Density 0.001%

    No Known Activations