© 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 EvalsExportsAPI 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. 42980
    Prev
    Next
    INDEX
    Explanations

    colors

    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
     levert
    -0.08
    리를
    -0.08
     bulun
    -0.07
    чна
    -0.07
     hurt
    -0.07
    Hur
    -0.07
    咨
    -0.07
    正
    -0.07
    Nie
    -0.07
    armaceutical
    -0.07
    POSITIVE LOGITS
     Spots
    0.09
     spots
    0.09
     cells
    0.08
     Tet
    0.08
     wszystkim
    0.08
     sky
    0.08
    -painted
    0.08
     остров
    0.07
    adecimal
    0.07
     విమ
    0.07
    Activations Density 0.012%

    No Known Activations