© 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. 111384
    Prev
    Next
    INDEX
    Explanations

    percentage calculations

    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
     Morse
    -0.08
     solitude
    -0.08
     amateur
    -0.08
     mundane
    -0.08
     NONE
    -0.08
    II
    -0.07
    ++++++++++++++++++++++++++++++++
    -0.07
     aburr
    -0.07
     engross
    -0.07
     Chapel
    -0.07
    POSITIVE LOGITS
     percentage
    0.11
    percent
    0.10
     Percentage
    0.10
    前年比
    0.10
    百分
    0.10
    percentage
    0.10
    _percent
    0.10
     porcent
    0.10
    .percent
    0.10
     শতাংশ
    0.10
    Activations Density 0.103%

    No Known Activations