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. 65900
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
    寶
    -0.08
     devra
    -0.08
     беше
    -0.08
     deberá
    -0.08
    _each
    -0.08
    -extra
    -0.07
     ønsk
    -0.07
     deberán
    -0.07
     Thi
    -0.07
     др
    -0.07
    POSITIVE LOGITS
     somehow
    0.08
    నా
    0.07
    是真的吗
    0.07
    걸
    0.07
     just
    0.07
    别人
    0.07
    ZW
    0.07
    ?”
    0.07
     contractual
    0.07
     collaborative
    0.07
    Activations Density 0.114%

    No Known Activations