© 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. 11-RESID-POST-AA
    11. 64554
    Prev
    Next
    INDEX
    Explanations

    26

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     birthdays
    -0.09
     aniversário
    -0.09
     cumpleaños
    -0.08
    scriber
    -0.08
     Counter
    -0.08
    τους
    -0.08
    upr
    -0.08
     الجم
    -0.08
     Contributions
    -0.08
    Ủ
    -0.08
    POSITIVE LOGITS
     spanning
    0.09
     longitudinal
    0.09
     contiguous
    0.08
     dài
    0.08
    连续
    0.07
     overlapping
    0.07
    贯
    0.07
     consecutive
    0.07
    鸣
    0.07
    0.07
    Activations Density 0.034%
    No Known Activations