© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112585
    Prev
    Next
    INDEX
    Explanations

    game controller input

    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
     contingency
    -0.08
    CREATE
    -0.08
     domic
    -0.08
    什么
    -0.08
     gee
    -0.07
     устро
    -0.07
    传播
    -0.07
     samb
    -0.07
     flyers
    -0.07
     sichere
    -0.07
    POSITIVE LOGITS
     الشاشة
    0.09
     हथ
    0.09
     HDD
    0.08
     labada
    0.08
    chmal
    0.08
    una
    0.08
    aptops
    0.08
    aptop
    0.08
    มือ
    0.08
     شاشة
    0.08
    Activations Density 0.001%

    No Known Activations