© 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. 103242
    Prev
    Next
    INDEX
    Explanations

    say "1"

    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
     دیگری
    -0.12
     última
    -0.10
     último
    -0.10
     ibang
    -0.10
     অন্য
    -0.09
     آخر
    -0.09
    最后
    -0.09
    最後
    -0.09
     دیگر
    -0.09
     второй
    -0.09
    POSITIVE LOGITS
     первом
    0.13
     الأولى
    0.13
     erste
    0.13
     第一
    0.12
     pierws
    0.12
     pertama
    0.12
    첫
    0.12
     первая
    0.11
     первого
    0.11
     primeira
    0.11
    Activations Density 0.073%

    No Known Activations