Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44632
    Prev
    Next
    INDEX
    Explanations

    Stop words

    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
     tarif
    -0.08
    身份证
    -0.08
    发布
    -0.07
    上映
    -0.07
    Startup
    -0.07
     الأداء
    -0.07
     pagal
    -0.07
     cybers
    -0.07
    发行
    -0.07
     בישראל
    -0.07
    POSITIVE LOGITS
     manually
    0.10
     utensils
    0.09
     extermin
    0.09
     salvage
    0.09
     reluctantly
    0.09
     spoon
    0.09
     jugu
    0.09
     vít
    0.09
     scav
    0.09
     debris
    0.09
    Activations Density 0.027%

    No Known Activations