© 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. 110330
    Prev
    Next
    INDEX
    Explanations

    Words ending in "ed" or "ers"

    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
    �
    -0.08
    ಿಗೂ
    -0.08
    ಮ
    -0.08
    确
    -0.07
    .ss
    -0.07
     Keep
    -0.07
     /*↵
    -0.07
    ulia
    -0.07
     verdade
    -0.07
    ಿಕ
    -0.07
    POSITIVE LOGITS
     (?)
    0.10
    且
    0.09
     (!)
    0.09
    (?)
    0.09
    、有
    0.08
    ，有
    0.08
    的吗
    0.07
    ，对
    0.07
    kur
    0.07
    =('
    0.07
    Activations Density 0.198%

    No Known Activations