© 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. 114291
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
    <i
    -0.07
    >())↵
    -0.07
    Coroutine
    -0.07
     plurality
    -0.07
    erezo
    -0.07
     serio
    -0.07
     contempor
    -0.07
    Biz
    -0.07
    *i
    -0.07
     kernels
    -0.07
    POSITIVE LOGITS
    ూమ
    0.09
     의견
    0.08
     Дума
    0.08
     дожд
    0.08
    μμα
    0.08
     amus
    0.08
    -angle
    0.08
    Ộ
    0.08
     lasse
    0.08
    ANGLES
    0.08
    Activations Density 0.028%

    No Known Activations