© 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. 3-RESID-POST-AA
    11. 13141
    Prev
    Next
    INDEX
    Explanations

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gl
    -0.08
     tricks
    -0.08
    gl
    -0.08
    Uid
    -0.08
     Gl
    -0.07
    月份
    -0.07
     precious
    -0.07
     Mahl
    -0.07
    RM
    -0.07
     glucose
    -0.07
    POSITIVE LOGITS
    观点
    0.14
     의견
    0.13
    意见
    0.13
    认为
    0.13
     opinions
    0.12
     skepticism
    0.11
     skeptical
    0.11
     Opinions
    0.11
     opinion
    0.10
    ความคิดเห็น
    0.10
    Activations Density 0.306%

    No Known Activations