© 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. 71372
    Prev
    Next
    INDEX
    Explanations

    Latin-like/gibberish text

    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
     Geheim
    -0.09
     батар
    -0.09
    ്റ്റ
    -0.08
    ТА
    -0.08
     Urbana
    -0.08
     Shed
    -0.08
     Shel
    -0.08
     ఎన
    -0.08
     bim
    -0.08
     electricians
    -0.08
    POSITIVE LOGITS
     Lorem
    0.16
     adipisicing
    0.16
    Lorem
    0.15
     consectetur
    0.15
     incididunt
    0.14
     tincidunt
    0.14
     lorem
    0.14
     adipiscing
    0.13
     ipsum
    0.13
     ullam
    0.12
    Activations Density 0.002%

    No Known Activations