© 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. 114254
    Prev
    Next
    INDEX
    Explanations

    Trentino-Alto Adige/Südtirol region

    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
    .df
    -0.09
    .NULL
    -0.08
     организ
    -0.08
     장소
    -0.08
     regula
    -0.08
     awhile
    -0.08
     langfrist
    -0.08
    otch
    -0.07
    aside
    -0.07
     organizing
    -0.07
    POSITIVE LOGITS
     alpine
    0.08
     Alps
    0.08
     Côte
    0.08
     estre
    0.08
     Conan
    0.08
     colorectal
    0.07
     Alpine
    0.07
     bagu
    0.07
     Clem
    0.07
     Cruc
    0.07
    Activations Density 0.009%

    No Known Activations