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. 27425
    Prev
    Next
    INDEX
    Explanations

    Project Management

    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
    -0.08
    axxer
    -0.07
     Schl
    -0.07
     lock
    -0.07
     cuck
    -0.07
    aughter
    -0.07
     ಚಾಲ
    -0.07
     دود
    -0.07
     Kish
    -0.07
    産
    -0.07
    POSITIVE LOGITS
     أعمال
    0.08
    områ
    0.07
    ieno
    0.07
     zelo
    0.07
    图库
    0.07
     الأعمال
    0.07
     WORK
    0.07
     categories
    0.07
     compliment
    0.07
     compartments
    0.07
    Activations Density 0.003%

    No Known Activations