© 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. 70955
    Prev
    Next
    INDEX
    Explanations

    programming contracts

    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
     בכלל
    -0.08
     algae
    -0.08
     combinatie
    -0.07
    Jeff
    -0.07
    swiper
    -0.07
     mogelijkheid
    -0.07
    _discount
    -0.07
     rank
    -0.07
     Wolfe
    -0.07
    חדש
    -0.07
    POSITIVE LOGITS
    接口
    0.10
    /interfaces
    0.09
    interfaces
    0.09
     interfaces
    0.09
    契
    0.09
    /interface
    0.09
     defined
    0.08
     deline
    0.08
     stö
    0.08
     интерф
    0.08
    Activations Density 0.007%

    No Known Activations