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

    Neuronpedia

    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. 102459
    Prev
    Next
    INDEX
    Explanations

    easily (in other 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
     pudiera
    -0.11
    进行了
    -0.09
     می
    -0.09
     tekur
    -0.09
     можа
    -0.08
    стың
    -0.08
    Could
    -0.08
    ่าสุด
    -0.08
    ίζεται
    -0.08
     putea
    -0.08
    POSITIVE LOGITS
     fácilmente
    0.20
     facilmente
    0.18
     بسهولة
    0.18
    ได้
    0.18
     facilement
    0.16
     easily
    0.16
     ได้
    0.15
    อนได้
    0.15
     akár
    0.14
     durchaus
    0.14
    Activations Density 0.503%

    No Known Activations