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. 76109
    Prev
    Next
    INDEX
    Explanations

    template adjustments

    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
    って
    -0.08
     enthusiasts
    -0.08
     oluş
    -0.08
    uidor
    -0.07
    初心
    -0.07
     Device
    -0.07
     уга
    -0.07
     estação
    -0.07
    gle
    -0.07
    薬
    -0.07
    POSITIVE LOGITS
     tailoring
    0.15
     tailored
    0.12
    Customize
    0.12
     Customize
    0.12
     customizing
    0.12
     personalization
    0.12
     customization
    0.12
     tailor
    0.11
     personalized
    0.11
     Anpass
    0.11
    Activations Density 0.013%

    No Known Activations