© 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 EvalsExportsinterp-engineNEWAPI 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. 69939
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
     बो
    -0.08
     Wiki
    -0.08
    265
    -0.07
     Burner
    -0.07
     Journalist
    -0.07
     bole
    -0.07
     hiervan
    -0.07
     give
    -0.07
    ocratic
    -0.07
     dovoljno
    -0.07
    POSITIVE LOGITS
     --->
    0.08
    (T
    0.08
     patriarch
    0.08
    Ctl
    0.08
    .cy
    0.08
    ออนไลน์
    0.08
    Ctrl
    0.08
     cortical
    0.08
    户
    0.07
     abroad
    0.07
    Activations Density 0.589%

    No Known Activations