© 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. 3-RESID-POST-AA
    11. 995
    Prev
    Next
    INDEX
    Explanations

    두

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devotion
    -0.08
     tuna
    -0.07
     Alte
    -0.07
     khe
    -0.07
     pitfalls
    -0.07
    یکار
    -0.07
    το
    -0.07
     Tuna
    -0.07
    ]]:↵
    -0.07
    INE
    -0.07
    POSITIVE LOGITS
    beh
    0.08
    con
    0.08
     לג
    0.08
    Han
    0.08
    gli
    0.07
     Mueller
    0.07
    wissen
    0.07
     negli
    0.07
     wee
    0.07
     exert
    0.07
    Activations Density 0.000%

    No Known Activations