© 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. 91870
    Prev
    Next
    INDEX
    Explanations

    Titan

    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
     अद
    -0.08
     Stephan
    -0.08
    chimp
    -0.08
    liness
    -0.07
     hyst
    -0.07
    Sj
    -0.07
     रह
    -0.07
    øy
    -0.07
     negro
    -0.07
    erken
    -0.07
    POSITIVE LOGITS
     près
    0.08
     дав
    0.08
     dioxide
    0.07
     обществ
    0.07
     Holds
    0.07
     sands
    0.07
     �
    0.07
    巨
    0.07
    /Header
    0.07
    дар
    0.07
    Activations Density 0.002%

    No Known Activations