© 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. 62995
    Prev
    Next
    INDEX
    Explanations

    clock

    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
     monot
    -0.08
     inco
    -0.07
     Ugly
    -0.07
     Sunda
    -0.07
     존
    -0.07
     стиль
    -0.07
    Mon
    -0.07
    ਠ
    -0.07
     ................................
    -0.07
     Tinder
    -0.07
    POSITIVE LOGITS
     boosts
    0.08
    是多少
    0.08
     Fallen
    0.08
     nel
    0.08
     achievable
    0.08
    -semibold
    0.08
    ôtes
    0.08
    並
    0.07
    বর্তী
    0.07
    ,J
    0.07
    Activations Density 0.002%

    No Known Activations