© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 51951
    Prev
    Next
    INDEX
    Explanations

    say "owanie"

    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
    ฐ
    -0.08
     NSDictionary
    -0.08
    BOOL
    -0.08
     vha
    -0.08
    �
    -0.08
    ाओं
    -0.08
     =================================
    -0.08
    nější
    -0.08
     quos
    -0.07
    েস
    -0.07
    POSITIVE LOGITS
    owanie
    0.25
    owania
    0.25
    owaniu
    0.22
    owany
    0.21
    owanych
    0.20
    owane
    0.20
    owana
    0.19
    owani
    0.18
    owan
    0.18
    ować
    0.16
    Activations Density 0.001%

    No Known Activations