© 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. 22707
    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
     lehen
    -0.08
    后来
    -0.08
    екоменду
    -0.08
     wcześniej
    -0.08
    前年
    -0.08
    首次
    -0.08
     następ
    -0.08
     ранее
    -0.08
     الأخيرة
    -0.08
     পরে
    -0.08
    POSITIVE LOGITS
     focus
    0.14
    -focused
    0.14
     Focus
    0.13
     fokus
    0.13
    Focused
    0.13
    Focus
    0.13
    focused
    0.13
    focus
    0.13
     집중
    0.12
     Fokus
    0.12
    Activations Density 0.030%

    No Known Activations