© 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. 26627
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
     cigarettes
    -0.09
     ambassadors
    -0.08
    .dashboard
    -0.08
     neurotrans
    -0.08
     sustancias
    -0.08
     smartphones
    -0.08
     restaurants
    -0.08
     Smartphones
    -0.08
     subsidies
    -0.07
     conscious
    -0.07
    POSITIVE LOGITS
     біблі
    0.11
    源码
    0.10
     strcpy
    0.10
     vendor
    0.10
     library
    0.10
    vendor
    0.10
    下载
    0.10
     நூ
    0.10
    cdnjs
    0.10
    /vendor
    0.10
    Activations Density 0.014%

    No Known Activations