© 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. 102265
    Prev
    Next
    INDEX
    Explanations

    Jim/James

    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
    ्यवाद
    -0.09
     بالفعل
    -0.09
     واقعی
    -0.08
     ولذلك
    -0.08
     typical
    -0.08
     hence
    -0.08
     العاصمة
    -0.08
     קיימ
    -0.08
     existent
    -0.08
     ενδια
    -0.08
    POSITIVE LOGITS
    énez
    0.16
    enez
    0.13
    on
    0.10
    ené
    0.10
    ি
    0.08
    tos
    0.08
    ma
    0.08
    othy
    0.08
    る
    0.08
    on's
    0.08
    Activations Density 0.007%

    No Known Activations