© 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. 15-RESID-POST-AA
    11. 16692
    Prev
    Next
    INDEX
    Explanations

    头

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Als
    -0.08
     We
    -0.08
     Texte
    -0.07
     LAN
    -0.07
     onverw
    -0.07
     launches
    -0.07
     Conduct
    -0.07
     Prints
    -0.07
    -life
    -0.07
    landing
    -0.07
    POSITIVE LOGITS
     בלבד
    0.10
     entirely
    0.09
     এসেছে
    0.09
     gewesen
    0.09
     geworden
    0.09
     bedoeld
    0.09
     gekommen
    0.09
    だった
    0.09
     odstr
    0.08
     spé
    0.08
    Activations Density 0.058%

    No Known Activations