© 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. 70585
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    WSTR
    -0.08
    reinterpret
    -0.08
     SWOT
    -0.08
    sic
    -0.08
    aderen
    -0.07
     Главное
    -0.07
    олот
    -0.07
    察
    -0.07
    桃
    -0.07
    ördin
    -0.07
    POSITIVE LOGITS
     legitimately
    0.12
     nuances
    0.09
     uneven
    0.08
     unforeseen
    0.08
     inadvert
    0.08
     differing
    0.08
     irregular
    0.08
     unrelated
    0.08
     malicious
    0.08
     malformed
    0.08
    Activations Density 0.043%

    No Known Activations