© 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. 45534
    Prev
    Next
    INDEX
    Explanations

    End of sentences

    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
    ':↵
    -0.09
     मृत
    -0.08
    {}'.
    -0.08
    腿
    -0.07
    ':
    -0.07
     legs
    -0.07
     Returns
    -0.07
     Eats
    -0.07
     मुफ
    -0.07
    ’:
    -0.07
    POSITIVE LOGITS
     impresionante
    0.08
    0.08
     chronic
    0.08
     magnifique
    0.07
     sut
    0.07
    .baidu
    0.07
     utak
    0.07
     svensk
    0.07
     sinh
    0.07
     indeb
    0.07
    Activations Density 0.000%
    No Known Activations