© 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. 18155
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    Negative Logits
    ").↵↵
    -0.11
     herhangi
    -0.11
    -0.10
    -0.10
    -0.10
    ）。↵↵
    -0.10
    -0.10
     ربما
    -0.10
    �ურ
    -0.10
     ڪنهن
    -0.10
    POSITIVE LOGITS
    =>
    0.12
     ((
    0.12
    ⇒
    0.11
     ((((
    0.11
     ⇒
    0.11
    :
    0.11
     (((
    0.11
     leads
    0.10
    (((
    0.10
    =((
    0.10
    Activations Density 0.038%
    No Known Activations