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

    Neuronpedia

    Jacobian LensNEW
    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. 64190
    Prev
    Next
    INDEX
    Explanations

    lambda

    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
    ही
    -0.08
     handing
    -0.07
     Ben
    -0.07
    ण्य
    -0.07
     ಕೂಡ
    -0.07
     Kol
    -0.07
    ड़क
    -0.07
     enj
    -0.07
    員
    -0.07
     rab
    -0.07
    POSITIVE LOGITS
    ENTITY
    0.08
    ambda
    0.08
    ค่
    0.08
    IAA
    0.08
    TIME
    0.07
    IPAddress
    0.07
    Reconnect
    0.07
    생
    0.07
    MAP
    0.07
    cloak
    0.07
    Activations Density 0.008%

    No Known Activations