© 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. 42979
    Prev
    Next
    INDEX
    Explanations

    vectors

    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
    adon
    -0.08
    快速
    -0.08
    �
    -0.07
    likle
    -0.07
    快捷
    -0.07
    loh
    -0.07
     سریع
    -0.07
     quicker
    -0.07
    -Mus
    -0.07
    _WS
    -0.07
    POSITIVE LOGITS
     vectors
    0.10
    Vectors
    0.09
     Position
    0.08
    .angle
    0.08
    Directions
    0.08
     Directions
    0.08
    irections
    0.08
     Span
    0.08
     verão
    0.08
     Try
    0.08
    Activations Density 0.016%

    No Known Activations