© 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. 23-RESID-POST-AA
    11. 50398
    Prev
    Next
    INDEX
    Explanations

    к

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ாள
    -0.09
    ாள்
    -0.09
    -0.08
    ុខ
    -0.08
     پیچ
    -0.08
    么
    -0.08
    ன்ப
    -0.08
     فائد
    -0.08
     Komple
    -0.07
    -0.07
    POSITIVE LOGITS
    édients
    0.10
    íbles
    0.09
    ensible
    0.09
    íble
    0.09
    avelmente
    0.09
    cate
    0.09
    ليزية
    0.08
    íduo
    0.08
    áveis
    0.08
    identes
    0.08
    Activations Density 0.018%

    No Known Activations