© 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. 19-RESID-POST-AA
    11. 18217
    Prev
    Next
    INDEX
    Explanations

    Game scores and statistics

    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
     questionnaire
    -0.09
     fonctionner
    -0.08
    Which
    -0.08
    هایی
    -0.08
     irgende
    -0.08
     geographic
    -0.08
    which
    -0.08
     lequel
    -0.08
    European
    -0.08
    。）↵↵
    -0.08
    POSITIVE LOGITS
     ▼
    0.12
     Lv
    0.11
     ●
    0.11
     ▲
    0.11
     Avg
    0.11
       　
    0.11
    □□□□□□□□
    0.10
     当前
    0.10
     ￥
    0.10
    ●
    0.10
    Activations Density 0.002%

    No Known Activations