© 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. 23-RESID-POST-AA
    11. 47935
    Prev
    Next
    INDEX
    Explanations

    truncated text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    晰
    -0.08
    enu
    -0.07
     pequeño
    -0.07
    wanag
    -0.07
    212
    -0.07
    .Utils
    -0.07
    itudes
    -0.07
    ends
    -0.07
     CLI
    -0.07
     apprécié
    -0.07
    POSITIVE LOGITS
    psons
    0.09
    онд
    0.08
    äss
    0.08
    ppelin
    0.08
    assin
    0.08
    pson
    0.07
    andering
    0.07
    abaw
    0.07
    idine
    0.07
    FORD
    0.07
    Activations Density 0.005%

    No Known Activations