© 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 EvalsExportsinterp-engineNEWAPI 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. 19526
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pyplot
    -0.08
    ：
    -0.08
    =tf
    -0.08
    excel
    -0.08
     حساب
    -0.08
    ，需要
    -0.08
    xlsx
    -0.07
     '↵↵
    -0.07
    amil
    -0.07
     وتس
    -0.07
    POSITIVE LOGITS
     flera
    0.09
    ">↵
    0.09
    "type
    0.09
    ?v
    0.08
    {/*
    0.08
     yabo
    0.08
    -type
    0.08
     nhiều
    0.08
     munk
    0.08
    .type
    0.08
    Activations Density 0.000%

    No Known Activations