© 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. 22334
    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
     Mk
    -0.08
     moest
    -0.08
     Os
    -0.08
     harus
    -0.07
     initiatief
    -0.07
     moet
    -0.07
     minério
    -0.07
    （）
    -0.07
    奋
    -0.07
     mkp
    -0.07
    POSITIVE LOGITS
     도움
    0.12
     मदद
    0.12
    专业
    0.12
     begeleiden
    0.12
     전문
    0.12
     professionals
    0.12
     helfen
    0.12
     tailored
    0.11
     विशेषज्ञ
    0.11
     professionelle
    0.11
    Activations Density 0.016%

    No Known Activations