© 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. 91322
    Prev
    Next
    INDEX
    Explanations

    equation

    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
    _bloc
    -0.08
    Bloc
    -0.08
     блок
    -0.08
    blok
    -0.08
    -0.08
    FCC
    -0.07
    Им
    -0.07
     personalized
    -0.07
     metabolism
    -0.07
    .EXTRA
    -0.07
    POSITIVE LOGITS
    圈
    0.08
    Thickness
    0.08
     circumference
    0.08
     piir
    0.08
     //--
    0.07
    这里只
    0.07
    0.07
     totalité
    0.07
     바
    0.07
     thickness
    0.07
    Activations Density 0.030%
    No Known Activations