© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110582
    Prev
    Next
    INDEX
    Explanations

    are

    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
    旨
    -0.08
    针
    -0.08
     Bets
    -0.08
     Mueller
    -0.07
     выз
    -0.07
     bacteria
    -0.07
     gren
    -0.07
    rex
    -0.07
    ிக்க
    -0.07
     પટ
    -0.07
    POSITIVE LOGITS
     idle
    0.09
     flight
    0.08
     fasting
    0.08
     paligid
    0.08
     commuting
    0.07
     everyday
    0.07
    -либо
    0.07
    idle
    0.07
    VA
    0.07
    angar
    0.07
    Activations Density 0.026%

    No Known Activations