© 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. 110305
    Prev
    Next
    INDEX
    Explanations

    static

    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
    /books
    -0.08
    REC
    -0.07
     brit
    -0.07
     otom
    -0.07
    immi
    -0.07
    走
    -0.07
    লা
    -0.07
     wb
    -0.07
     vers
    -0.07
     Porte
    -0.07
    POSITIVE LOGITS
     Bengali
    0.08
     Pleasant
    0.07
    ообраз
    0.07
     კომ
    0.07
     сниж
    0.07
     воздейств
    0.07
    akho
    0.07
     сниз
    0.07
     duurzaamheid
    0.07
    OPLE
    0.07
    Activations Density 0.001%

    No Known Activations