© 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. 70894
    Prev
    Next
    INDEX
    Explanations

    statistical modeling

    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
    tail
    -0.08
     கூட
    -0.08
     house
    -0.08
     Park
    -0.08
    Tail
    -0.08
     tail
    -0.08
     Holden
    -0.08
    _suffix
    -0.08
     Tail
    -0.08
    _tail
    -0.08
    POSITIVE LOGITS
     vulnerabilities
    0.08
     देखें
    0.08
     IQ
    0.08
     vulner
    0.08
     vuln
    0.07
    0.07
    _IP
    0.07
     acne
    0.07
    _PH
    0.07
    堵
    0.07
    Activations Density 0.001%
    No Known Activations