© 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. 54636
    Prev
    Next
    INDEX
    Explanations

    as

    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
     recreation
    -0.10
    ೇವೆ
    -0.09
     recreational
    -0.08
     recovering
    -0.08
     quarant
    -0.08
     ausser
    -0.08
     antivirus
    -0.08
    Screens
    -0.08
     Uncategorized
    -0.08
     sleeping
    -0.08
    POSITIVE LOGITS
    bucks
    0.08
     সিন
    0.08
    _SY
    0.08
     বিরুদ্ধে
    0.07
    _COMPARE
    0.07
     বাক
    0.07
    _BR
    0.07
    _phrase
    0.07
    -br
    0.07
    raak
    0.07
    Activations Density 0.012%

    No Known Activations