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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45621
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     oft
    -0.08
     |↵
    -0.07
    Plus
    -0.07
    ({});↵
    -0.07
    �
    -0.07
     overhaul
    -0.07
     wear
    -0.07
    -plus
    -0.07
    ाशी
    -0.07
    unis
    -0.07
    POSITIVE LOGITS
     consecutive
    0.09
     തമ്മ
    0.08
     যাচ্ছে
    0.08
    erz
    0.08
     IRead
    0.08
     Ending
    0.08
     spaced
    0.08
     estaria
    0.08
    ક્રમ
    0.08
     leerling
    0.08
    Activations Density 0.028%

    No Known Activations