© 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. 114166
    Prev
    Next
    INDEX
    Explanations

    punctuation in code

    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
     albeit
    -0.08
    관련
    -0.07
     مذ
    -0.07
    bk
    -0.07
    mdb
    -0.07
    averse
    -0.07
     variety
    -0.07
     clar
    -0.07
     typical
    -0.07
    awk
    -0.06
    POSITIVE LOGITS
     soov
    0.09
     оплаты
    0.09
     outset
    0.09
     начале
    0.09
     raiz
    0.09
     रु
    0.09
     लोगो
    0.09
     Saul
    0.08
    635
    0.08
     Olympia
    0.08
    Activations Density 0.009%

    No Known Activations