© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102854
    Prev
    Next
    INDEX
    Explanations

    because in different languages

    np_max-act-logits · gemini-2.0-flash
    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
     usw
    -0.11
    ,etc
    -0.11
     등에
    -0.11
    等等
    -0.11
     વગેરે
    -0.11
     etc
    -0.11
     וכו
    -0.10
     등의
    -0.10
     आदि
    -0.10
    (any
    -0.10
    POSITIVE LOGITS
     because
    0.20
     since
    0.19
    ，因为
    0.18
     çünkü
    0.18
     क्योंकि
    0.17
     لأنه
    0.16
     ponieważ
    0.16
     deoarece
    0.16
     eftersom
    0.15
     ngoba
    0.15
    Activations Density 0.070%

    No Known Activations