© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 21127
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     malen
    -0.09
     артист
    -0.08
     cómo
    -0.08
     চলচ্চ
    -0.08
     hvordan
    -0.08
    .features
    -0.08
     hvernig
    -0.08
     artwork
    -0.07
    .orig
    -0.07
     шығарм
    -0.07
    POSITIVE LOGITS
    뢰
    0.13
    任
    0.13
     भरो
    0.12
     confiance
    0.12
    赖
    0.12
    頼
    0.11
     confianza
    0.11
    可信
    0.11
     vertrouwen
    0.11
     confiança
    0.11
    Activations Density 0.001%

    No Known Activations