© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110595
    Prev
    Next
    INDEX
    Explanations

    hateful

    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
     Guillermo
    -0.08
     Miguel
    -0.08
     ped
    -0.07
     minu
    -0.07
     oportunidades
    -0.07
     Ana
    -0.07
     procuram
    -0.07
     왕
    -0.07
     сделали
    -0.07
    镇
    -0.07
    POSITIVE LOGITS
     racism
    0.11
     racist
    0.10
     stereotypes
    0.09
     persecution
    0.09
     protesting
    0.09
     kanker
    0.09
     наруш
    0.09
     racial
    0.09
     hatred
    0.09
     violates
    0.08
    Activations Density 0.011%

    No Known Activations