© 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. 7-RESID-POST-AA
    11. 1147
    Prev
    Next
    INDEX
    Explanations

    Visual Studio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impulses
    -0.08
     convictions
    -0.07
     λόγ
    -0.07
    মাত্র
    -0.07
     persec
    -0.07
     proph
    -0.07
    ベル
    -0.07
    ún
    -0.07
     разм
    -0.07
    .session
    -0.07
    POSITIVE LOGITS
     Cine
    0.09
     LLP
    0.09
     Intelli
    0.08
     oncology
    0.08
     culin
    0.08
     cine
    0.08
     fosse
    0.08
     Everest
    0.08
    ixe
    0.07
     Monaco
    0.07
    Activations Density 0.004%

    No Known Activations