© 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. 7448
    Prev
    Next
    INDEX
    Explanations

    want will

    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
    уть
    -0.09
    、更
    -0.08
    інде
    -0.08
     cori
    -0.08
    ూట
    -0.08
     업체
    -0.08
    demo
    -0.08
     pudd
    -0.08
     définitivement
    -0.08
     sheen
    -0.08
    POSITIVE LOGITS
     Genre
    0.08
     Beg
    0.07
     Your
    0.07
     Angst
    0.07
     ഞാൻ
    0.07
     Personal
    0.07
     schl
    0.07
     hierbij
    0.07
     私
    0.07
    DUCT
    0.07
    Activations Density 0.018%

    No Known Activations