© 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. 112331
    Prev
    Next
    INDEX
    Explanations

    CNN

    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
    技
    -0.08
     umb
    -0.07
     upe
    -0.07
     пред
    -0.07
     бес
    -0.07
     सरकारी
    -0.07
     सम्म
    -0.07
     functionality
    -0.07
     config
    -0.07
    .Write
    -0.07
    POSITIVE LOGITS
     entlang
    0.10
     Marzo
    0.09
     paragraphs
    0.09
     Temporal
    0.08
    Temporal
    0.08
     Craw
    0.08
     ingestion
    0.08
     Kurz
    0.08
     органы
    0.08
     paragraph
    0.08
    Activations Density 0.002%

    No Known Activations