© 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. 112707
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    gu
    -0.08
     Gui
    -0.08
     greeted
    -0.07
     hast
    -0.07
     gì
    -0.07
     entraîner
    -0.07
     verfolgen
    -0.07
    यू
    -0.07
    Beginning
    -0.07
    ٌ
    -0.07
    POSITIVE LOGITS
     union
    0.08
     parity
    0.07
    unny
    0.07
    183
    0.07
     &=
    0.07
    妻
    0.07
    union
    0.07
    象
    0.07
    偶
    0.07
    ral
    0.07
    Activations Density 0.020%

    No Known Activations