© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 1091
    Prev
    Next
    INDEX
    Explanations

    who knows, speculation

    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
     DU
    -0.07
     desem
    -0.07
     reside
    -0.07
    -0.07
    -pal
    -0.07
    ță
    -0.07
     residência
    -0.07
     REV
    -0.07
    outine
    -0.07
    -Sm
    -0.07
    POSITIVE LOGITS
    /Web
    0.09
     ituaiga
    0.08
    般
    0.08
    0.08
     ก็
    0.07
     fades
    0.07
    ფერ
    0.07
     mystérie
    0.07
     Heaven
    0.07
     fechado
    0.07
    Activations Density 0.005%

    No Known Activations