© 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. 22343
    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
     midnight
    -0.08
     Memories
    -0.08
     заң
    -0.08
     weddings
    -0.08
     memories
    -0.08
     খুল
    -0.08
     subpo
    -0.08
    Leaks
    -0.07
     wires
    -0.07
    cstring
    -0.07
    POSITIVE LOGITS
    评分
    0.41
    评级
    0.37
     Bewertung
    0.34
     rating
    0.34
     bewertet
    0.33
    คะแนน
    0.33
     scoring
    0.33
     рейтинг
    0.32
     ratings
    0.32
     평가
    0.31
    Activations Density 0.117%

    No Known Activations