© 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. 71206
    Prev
    Next
    INDEX
    Explanations

    negative

    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
     Catholic
    -0.09
     prayer
    -0.08
     scholarship
    -0.08
     religious
    -0.08
     religiosos
    -0.08
     scholarly
    -0.08
    ("/
    -0.07
     divides
    -0.07
    .loaded
    -0.07
    eid
    -0.07
    POSITIVE LOGITS
     negat
    0.11
     negativity
    0.09
     Negative
    0.09
    -negative
    0.09
     negative
    0.09
     negatif
    0.09
    negative
    0.09
    Negative
    0.09
     unnatural
    0.08
     negativa
    0.08
    Activations Density 0.026%

    No Known Activations