© 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 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. 113367
    Prev
    Next
    INDEX
    Explanations

    xy

    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
    _FALSE
    -0.08
     Heard
    -0.08
    TACT
    -0.08
    ήσεις
    -0.08
    _TRUE
    -0.08
    .optim
    -0.07
     methodologies
    -0.07
     Mechanical
    -0.07
    满意
    -0.07
    _BIND
    -0.07
    POSITIVE LOGITS
     arg
    0.08
     espécie
    0.08
     camp
    0.07
     respiratory
    0.07
    ル
    0.07
     hatten
    0.07
     koordin
    0.07
     jk
    0.07
     compassion
    0.07
     especie
    0.07
    Activations Density 0.010%

    No Known Activations