© 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. 51994
    Prev
    Next
    INDEX
    Explanations

    الع

    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
    ření
    -0.09
     Μα
    -0.08
     ma
    -0.08
    家乐
    -0.08
     Mum
    -0.07
    Mat
    -0.07
    ()',
    -0.07
    жи
    -0.07
    -0.07
    -ma
    -0.07
    POSITIVE LOGITS
    اط
    0.16
    وا
    0.11
    �
    0.09
     эмоцион
    0.09
    طف
    0.09
     emocional
    0.09
     ემ
    0.09
    060
    0.08
     emos
    0.08
    ಾವ
    0.08
    Activations Density 0.001%
    No Known Activations