© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 47473
    Prev
    Next
    INDEX
    Explanations

    text processing/parsing

    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
    喘
    -0.08
     ember
    -0.07
     ко
    -0.07
     toil
    -0.07
     sore
    -0.07
     zel
    -0.07
    ետր
    -0.07
    :↵↵↵↵
    -0.07
    ութ
    -0.07
     koj
    -0.07
    POSITIVE LOGITS
    Bj
    0.08
    odge
    0.08
     initials
    0.08
    凡
    0.08
    maj
    0.07
     autón
    0.07
    urricular
    0.07
     Turismo
    0.07
    额
    0.07
    ]<
    0.07
    Activations Density 0.000%

    No Known Activations