© 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. 69897
    Prev
    Next
    INDEX
    Explanations

    Bleach

    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
     Love
    -0.09
     liefde
    -0.09
     virus
    -0.08
     aşk
    -0.08
     loves
    -0.08
     váll
    -0.08
     love
    -0.08
    -video
    -0.08
     любовь
    -0.08
     પ્રેમ
    -0.08
    POSITIVE LOGITS
    akana
    0.08
     unions
    0.08
     ush
    0.07
     earthly
    0.07
    স্য
    0.07
     SATA
    0.07
     officers
    0.07
     kuy
    0.07
     numerous
    0.07
    มือ
    0.07
    Activations Density 0.001%

    No Known Activations