© 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. 110258
    Prev
    Next
    INDEX
    Explanations

    +

    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
     mahu
    -0.08
     hott
    -0.08
    چه
    -0.08
    .Simple
    -0.08
    ്ശ
    -0.07
     decentralized
    -0.07
     ayy
    -0.07
     కుమ
    -0.07
     squash
    -0.07
     arty
    -0.07
    POSITIVE LOGITS
     anos
    0.08
     godine
    0.08
     বছর
    0.08
     વર્ષે
    0.08
     años
    0.08
     jährlich
    0.08
     அன்று
    0.08
     wavelengths
    0.08
     years
    0.08
     decades
    0.08
    Activations Density 0.015%

    No Known Activations