© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 64976
    Prev
    Next
    INDEX
    Explanations

    frac

    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
    اضی
    -0.07
     basically
    -0.07
    _seed
    -0.07
    _lat
    -0.07
     hyper
    -0.07
    doctor
    -0.07
    cy
    -0.07
     apopt
    -0.07
    hyper
    -0.07
    主义
    -0.07
    POSITIVE LOGITS
     keber
    0.08
     પ્રવ
    0.07
    .accept
    0.07
     Ezra
    0.07
    બી
    0.07
     البعض
    0.07
    .Dev
    0.07
     bane
    0.07
     बजे
    0.07
     Bier
    0.07
    Activations Density 0.024%

    No Known Activations