© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24577
    Prev
    Next
    INDEX
    Explanations

    Cleaning and detailing

    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
    (Size
    -0.09
     mëny
    -0.08
     Devices
    -0.08
     fleeting
    -0.08
     Messaging
    -0.08
     اعلام
    -0.07
     cruel
    -0.07
    sizes
    -0.07
    涯
    -0.07
     Probability
    -0.07
    POSITIVE LOGITS
     cleanliness
    0.12
     immaculate
    0.12
     impec
    0.12
     spotless
    0.11
     sạch
    0.11
    -clean
    0.11
     limpieza
    0.11
    .clean
    0.11
    Clean
    0.11
     cleaned
    0.11
    Activations Density 0.075%

    No Known Activations