© 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. 71265
    Prev
    Next
    INDEX
    Explanations

    the

    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
     годов
    -0.09
     rents
    -0.09
     насос
    -0.09
     эх
    -0.09
     绥
    -0.09
     hores
    -0.08
     Symphony
    -0.08
     Lease
    -0.08
     fraî
    -0.08
     estreno
    -0.08
    POSITIVE LOGITS
     UNICEF
    0.09
     GCSE
    0.08
    小学
    0.08
     Classroom
    0.08
     school
    0.07
    React
    0.07
    Blockly
    0.07
     playful
    0.07
     })
    0.07
    家庭
    0.07
    Activations Density 0.101%

    No Known Activations