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. 98287
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    .consumer
    -0.08
     clutch
    -0.08
     ontmo
    -0.08
     ومع
    -0.08
    Steven
    -0.07
     grinders
    -0.07
    Ganz
    -0.07
     homeschooling
    -0.07
    clam
    -0.07
    gah
    -0.07
    POSITIVE LOGITS
     ling
    0.08
     Ling
    0.08
     বার
    0.08
    ี้
    0.08
     concaten
    0.07
     όσο
    0.07
    Ling
    0.07
    ôn
    0.07
    句话
    0.07
     Persian
    0.07
    Activations Density 0.003%

    No Known Activations