© 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. 71181
    Prev
    Next
    INDEX
    Explanations

    join

    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
    ($"
    -0.09
     promociones
    -0.09
    Businesses
    -0.08
     casinos
    -0.08
     celebrities
    -0.08
     Carousel
    -0.08
     ushort
    -0.08
     marketers
    -0.08
    Teen
    -0.08
     businesses
    -0.08
    POSITIVE LOGITS
     dissertation
    0.14
     교수
    0.13
    论文
    0.12
     Dissertation
    0.12
    科研
    0.12
    导师
    0.12
    博士
    0.12
     MATLAB
    0.11
     Harvard
    0.11
     Matlab
    0.11
    Activations Density 0.047%

    No Known Activations