© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78030
    Prev
    Next
    INDEX
    Explanations

    ^

    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
     qualitative
    -0.08
     closets
    -0.08
    儿
    -0.08
     qualit
    -0.07
     closet
    -0.07
    astra
    -0.07
    论
    -0.07
    qondo
    -0.07
    .dr
    -0.07
     describe
    -0.07
    POSITIVE LOGITS
    9
    0.09
    441
    0.08
     quatre
    0.08
     cuatro
    0.08
    44
    0.08
     quattro
    0.08
    6
    0.08
    429
    0.08
    305
    0.08
    steam
    0.08
    Activations Density 0.048%

    No Known Activations