© 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. 70691
    Prev
    Next
    INDEX
    Explanations

    Christ/Christianity

    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
     Lade
    -0.09
     Rag
    -0.09
     传真
    -0.08
     REG
    -0.08
     funk
    -0.08
     Peek
    -0.08
     souris
    -0.08
     �
    -0.07
     Fancy
    -0.07
     Backyard
    -0.07
    POSITIVE LOGITS
    vai
    0.09
    'um
    0.08
    他
    0.08
    tributor
    0.08
     circulação
    0.08
    usaha
    0.08
    itive
    0.07
    heal
    0.07
     illness
    0.07
     आँ
    0.07
    Activations Density 0.010%

    No Known Activations