© 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. 110988
    Prev
    Next
    INDEX
    Explanations

    to

    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
    মূল
    -0.08
     লাগ
    -0.08
     Bren
    -0.08
    оже
    -0.08
     fatalities
    -0.07
    ukum
    -0.07
    ukken
    -0.07
     Williams
    -0.07
    /max
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    تا
    0.08
     fore
    0.08
     aman
    0.08
     sord
    0.07
     видеть
    0.07
    การ
    0.07
     Nah
    0.07
     participate
    0.07
     menikmati
    0.07
     effectuer
    0.07
    Activations Density 0.016%

    No Known Activations