© 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. 95891
    Prev
    Next
    INDEX
    Explanations

    in

    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
    pin
    -0.07
    긴
    -0.07
    coming
    -0.07
    ाण
    -0.07
    apa
    -0.07
    PIN
    -0.07
     säker
    -0.07
    র্থ
    -0.07
    (secret
    -0.07
    (chart
    -0.07
    POSITIVE LOGITS
     herein
    0.09
     hospitalized
    0.08
     wholesale
    0.07
     fingertips
    0.07
     nossas
    0.07
     witte
    0.07
    راك
    0.07
     白
    0.07
     nossos
    0.07
     ances
    0.07
    Activations Density 0.013%

    No Known Activations