© 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 EvalsExportsAPI 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. 20149
    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
    ՝
    -0.12
    টি
    -0.10
    ில்
    -0.10
    ন্ন
    -0.09
     ցանկացած
    -0.09
    বর্তী
    -0.09
     מתאים
    -0.09
    র্ধ
    -0.09
    ੍ਹ
    -0.09
     بررسی
    -0.09
    POSITIVE LOGITS
     doesnt
    0.15
     arent
    0.15
     wasnt
    0.13
     alot
    0.13
     seperate
    0.13
     wouldnt
    0.13
     theres
    0.12
     didnt
    0.12
     i'll
    0.11
     isnt
    0.11
    Activations Density 5.121%

    No Known Activations