© 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. 95666
    Prev
    Next
    INDEX
    Explanations

    and,

    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
    stdbool
    -0.08
     volled
    -0.08
    aterial
    -0.08
    Narr
    -0.08
     zwi
    -0.08
    ಿಸಲಾಗ
    -0.07
    soft
    -0.07
    inder
    -0.07
    niv
    -0.07
    标
    -0.07
    POSITIVE LOGITS
     commerce
    0.09
     pulsa
    0.09
    奋斗
    0.08
     lived
    0.08
     laughing
    0.08
     dying
    0.08
    \.
    0.08
     Feliz
    0.07
     vida
    0.07
     feliz
    0.07
    Activations Density 0.031%

    No Known Activations