© 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. 111026
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    怎么看
    -0.09
     mwing
    -0.09
     للن
    -0.08
    什么意思
    -0.08
    Bases
    -0.08
     dhidi
    -0.08
     bunk
    -0.08
    ಡುವ
    -0.08
     แบบ
    -0.08
     มิ
    -0.08
    POSITIVE LOGITS
     bijvoorbeeld
    0.09
     :)
    0.08
    например
    0.08
    例えば
    0.08
     например
    0.08
     péld
    0.08
     suitably
    0.07
    })
    0.07
     logra
    0.07
     passend
    0.07
    Activations Density 0.075%

    No Known Activations