© 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. 19-RESID-POST-AA
    11. 18927
    Prev
    Next
    INDEX
    Explanations

    calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಿದ್ದ
    -0.08
    ಿತ್ರ
    -0.08
    imensional
    -0.08
     gewerkt
    -0.08
    ೊಳ
    -0.08
    ต์
    -0.08
     gyd
    -0.08
     माना
    -0.07
    ði
    -0.07
     afer
    -0.07
    POSITIVE LOGITS
    اڻ
    0.09
    שט
    0.08
    탁
    0.08
    vais
    0.08
     ప్రస్తుతం
    0.08
    سۇ
    0.07
    allar
    0.07
    nä
    0.07
     వల్ల
    0.07
     insbesondere
    0.07
    Activations Density 0.210%

    No Known Activations