© 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. 19-RESID-POST-AA
    11. 103360
    Prev
    Next
    INDEX
    Explanations

    Code comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (↵
    -0.09
    ovendien
    -0.08
     त्या
    -0.08
    (...)
    -0.08
    ([↵
    -0.08
     zudem
    -0.08
    Impro
    -0.08
     Zudem
    -0.08
     Bovendien
    -0.08
    That
    -0.08
    POSITIVE LOGITS
     //_
    0.18
     //$
    0.18
    //$
    0.17
     <!--<
    0.16
     //{↵
    0.13
     //'
    0.13
    #print
    0.13
    //#
    0.12
     {{--<
    0.12
     //[
    0.11
    Activations Density 0.005%

    No Known Activations