© 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. 19444
    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
    -ից
    -0.09
    таж
    -0.08
     નાખ
    -0.08
     deducted
    -0.08
     legado
    -0.08
     Dafür
    -0.08
    க்கு
    -0.08
     toegevoegd
    -0.08
     కు
    -0.08
     liep
    -0.08
    POSITIVE LOGITS
    式
    0.16
    ive
    0.12
    於
    0.12
    于
    0.12
    형
    0.11
    ivity
    0.11
    iveness
    0.10
    ively
    0.10
    মান
    0.10
    型
    0.10
    Activations Density 0.012%

    No Known Activations