© 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. 91749
    Prev
    Next
    INDEX
    Explanations

    legal scenarios

    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
    arai
    -0.10
    ----------------------------------------------------------------------------------------------------------------
    -0.09
     escenario
    -0.09
    平台注册
    -0.09
     Plataforma
    -0.09
    tlement
    -0.09
    --------------------------------------------------------------------------------
    -0.08
     initialise
    -0.08
     Па
    -0.08
    algo
    -0.08
    POSITIVE LOGITS
     Generally
    0.09
     negligent
    0.09
     lawful
    0.09
     covenant
    0.09
     construed
    0.09
     ನ್ಯಾಯ
    0.09
     ejus
    0.09
     vested
    0.09
     يجوز
    0.09
     Lord
    0.08
    Activations Density 0.090%

    No Known Activations