© 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. 44481
    Prev
    Next
    INDEX
    Explanations

    D

    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
     созда
    -0.08
    apit
    -0.07
    雅黑
    -0.07
    board
    -0.07
    ahl
    -0.07
    =yes
    -0.07
    ное
    -0.07
     Shields
    -0.07
     interc
    -0.07
     conducted
    -0.07
    POSITIVE LOGITS
     incarnation
    0.08
     رحم
    0.08
     wrath
    0.08
     godinu
    0.08
     relinqu
    0.08
    ుణ
    0.08
    ASC
    0.07
    /tools
    0.07
    Chron
    0.07
     timest
    0.07
    Activations Density 0.001%

    No Known Activations