© 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 EvalsExportsinterp-engineNEWAPI 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. 22212
    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
     dath
    -0.10
    adakan
    -0.09
    トラックバック
    -0.09
    -paying
    -0.09
     이벤트
    -0.09
     ntaub
    -0.09
     डेटा
    -0.08
    -launch
    -0.08
    ၚ
    -0.08
     أحداث
    -0.08
    POSITIVE LOGITS
     simpl
    0.18
     reduction
    0.17
     réduction
    0.15
    Reduction
    0.15
     reductions
    0.15
    Simpl
    0.14
     Reduction
    0.14
     reducción
    0.14
     reduce
    0.14
     azalt
    0.14
    Activations Density 0.042%

    No Known Activations