© 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. 69245
    Prev
    Next
    INDEX
    Explanations

    computer mouse cursor movement

    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
    課
    -0.10
    票
    -0.08
     추진
    -0.08
     matériaux
    -0.08
    _uuid
    -0.08
    .booking
    -0.08
     Admissions
    -0.08
     मस
    -0.08
    运营
    -0.08
     고민
    -0.08
    POSITIVE LOGITS
    mousemove
    0.12
    移动
    0.12
     mouse
    0.11
     Mouse
    0.10
    (mouse
    0.10
    .Move
    0.09
    mouse
    0.09
     bewegen
    0.09
    Mouse
    0.09
    鼠
    0.09
    Activations Density 0.007%

    No Known Activations