© 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. 110583
    Prev
    Next
    INDEX
    Explanations

    data scaling/label encoding

    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
     matemática
    -0.08
     mathem
    -0.08
     mathematic
    -0.07
    指定
    -0.07
     Power
    -0.07
    738
    -0.07
     perceived
    -0.07
     yake
    -0.07
    想
    -0.07
     anomal
    -0.07
    POSITIVE LOGITS
    .mapping
    0.09
    _mapping
    0.08
     tillbaka
    0.08
    กลับ
    0.08
    mapping
    0.08
     devuelve
    0.08
     mapping
    0.08
    .return
    0.08
    Mappings
    0.08
     العودة
    0.08
    Activations Density 0.003%

    No Known Activations