© 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. 3-RESID-POST-AA
    11. 13164
    Prev
    Next
    INDEX
    Explanations

    Lists and Enumerations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pur
    -0.08
    wp
    -0.07
    _RELEASE
    -0.07
     LPARAM
    -0.07
    Cats
    -0.07
    /wp
    -0.07
     usadas
    -0.07
    ínas
    -0.07
     pur
    -0.07
     preaching
    -0.07
    POSITIVE LOGITS
     Lor
    0.08
    halte
    0.08
    Lor
    0.08
     IAS
    0.07
     Dynasty
    0.07
    orable
    0.07
    irmer
    0.07
     निर्माता
    0.07
    su
    0.07
     fabricant
    0.07
    Activations Density 0.003%

    No Known Activations