© 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. 19728
    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
     байх
    -0.08
     sembl
    -0.08
    :");↵↵
    -0.07
     möj
    -0.07
    ումներ
    -0.07
    Around
    -0.07
    ելու
    -0.07
     около
    -0.07
     zogenaamde
    -0.07
     একটা
    -0.07
    POSITIVE LOGITS
     because
    0.17
     since
    0.16
    ，因为
    0.15
     क्योंकि
    0.15
     Çünkü
    0.15
     deoarece
    0.14
     omdat
    0.14
     لأنه
    0.14
    because
    0.14
    因为
    0.13
    Activations Density 0.064%

    No Known Activations