© 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. 49037
    Prev
    Next
    INDEX
    Explanations

    say "w" word

    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
    edra
    -0.08
     משה
    -0.08
    צות
    -0.08
     αυτού
    -0.08
    luss
    -0.08
    ąć
    -0.08
     liet
    -0.07
     själva
    -0.07
     Ака
    -0.07
    йс
    -0.07
    POSITIVE LOGITS
    AGMENT
    0.08
     Wire
    0.07
     spectroscopy
    0.07
    0.07
     Heidelberg
    0.07
    قط
    0.07
    _ray
    0.07
     Gam
    0.07
     гориз
    0.07
    öger
    0.07
    Activations Density 0.001%
    No Known Activations