© 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. 69242
    Prev
    Next
    INDEX
    Explanations

    people

    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
    山县
    -0.08
     datap
    -0.08
     War
    -0.08
     chur
    -0.08
    ტი
    -0.07
     тра
    -0.07
     thumb
    -0.07
     لڳ
    -0.07
    ufuna
    -0.07
    uvan
    -0.07
    POSITIVE LOGITS
    姓名
    0.09
     sexe
    0.08
    昵称
    0.08
    男女
    0.08
    Sex
    0.08
     Makeup
    0.08
     suivants
    0.08
    acters
    0.08
    :innen
    0.08
    vern
    0.07
    Activations Density 0.028%

    No Known Activations