© 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. 18132
    Prev
    Next
    INDEX
    Explanations

    for

    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
     referenced
    -0.08
     маан
    -0.08
    >-
    -0.08
     boleng
    -0.08
    >Hello
    -0.08
    охож
    -0.08
     mær
    -0.08
    텍
    -0.08
     मुदा
    -0.08
     있음
    -0.08
    POSITIVE LOGITS
     instructions
    0.21
     كيفية
    0.21
     Anleitung
    0.19
     советы
    0.19
     guidance
    0.18
     consejos
    0.18
    instructions
    0.18
     инструкции
    0.18
     advice
    0.18
     conseils
    0.18
    Activations Density 0.020%

    No Known Activations