© 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. 18188
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     પરંતુ
    -0.10
     поэтому
    -0.09
     ಆದರೆ
    -0.09
     पण
    -0.08
     لكن
    -0.08
     이에
    -0.08
     لذلك
    -0.08
    には
    -0.08
     그러나
    -0.08
     tetapi
    -0.08
    POSITIVE LOGITS
     conseguimos
    0.18
     можно
    0.15
     ontstaat
    0.15
     możemy
    0.15
     podremos
    0.15
     consigue
    0.15
     얻
    0.15
     podrás
    0.14
     galima
    0.14
     можна
    0.14
    Activations Density 0.064%

    No Known Activations