© 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. 65343
    Prev
    Next
    INDEX
    Explanations

    state

    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
     Robin
    -0.08
    Cla
    -0.08
    ”活动
    -0.08
     dolayı
    -0.08
    ibur
    -0.08
    ولې
    -0.08
     Wrest
    -0.07
    lié
    -0.07
     výro
    -0.07
    ){
    -0.07
    POSITIVE LOGITS
     freezes
    0.09
     trusting
    0.09
    .todos
    0.08
     freeze
    0.08
     updater
    0.08
    0.08
     updating
    0.08
     frozen
    0.08
    404
    0.07
     froze
    0.07
    Activations Density 0.002%
    No Known Activations