© 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. 114293
    Prev
    Next
    INDEX
    Explanations

    longitude

    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
     bacteria
    -0.08
     सिद्ध
    -0.08
     inoc
    -0.07
     מהם
    -0.07
     bacterial
    -0.07
     referee
    -0.07
     truly
    -0.07
     dance
    -0.07
     doors
    -0.07
     procur
    -0.07
    POSITIVE LOGITS
    greg
    0.08
     longitude
    0.08
     Greenwich
    0.08
    Longitude
    0.08
    乘
    0.08
    =obj
    0.08
     Blackburn
    0.08
    longitude
    0.08
    рами
    0.08
    北京时间
    0.08
    Activations Density 0.003%

    No Known Activations