© 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. 110986
    Prev
    Next
    INDEX
    Explanations

    Statistical and medical research

    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
     kriter
    -0.08
    巴黎
    -0.07
    مس
    -0.07
    .lat
    -0.07
     Mint
    -0.07
    .Arr
    -0.07
     consisting
    -0.07
    .edit
    -0.07
    .ed
    -0.07
     ਪ੍ਰ
    -0.07
    POSITIVE LOGITS
    bea
    0.08
    NF
    0.08
     quite
    0.08
     tw
    0.08
    worms
    0.07
    oner
    0.07
    annies
    0.07
     nah
    0.07
     lush
    0.07
     rhyme
    0.07
    Activations Density 0.003%

    No Known Activations