© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6485
    Prev
    Next
    INDEX
    Explanations

    mon

    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
     governs
    -0.09
     Fayette
    -0.09
    Enviar
    -0.08
     proves
    -0.08
    utes
    -0.08
    вы
    -0.08
    UTES
    -0.08
     DMV
    -0.08
    ίν
    -0.08
     Regents
    -0.08
    POSITIVE LOGITS
    key
    0.12
    .key
    0.10
     key
    0.10
    te
    0.10
    os
    0.10
    et
    0.09
    ologic
    0.09
    opol
    0.08
    -key
    0.08
    	key
    0.08
    Activations Density 0.003%

    No Known Activations