© 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. 48822
    Prev
    Next
    INDEX
    Explanations

    ]

    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
    <Transaction
    -0.10
    .Transaction
    -0.10
     navigating
    -0.10
    事务
    -0.10
    .transaction
    -0.10
    ➡
    -0.09
    ,.
    -0.09
    ❤️
    -0.09
     transaction
    -0.09
     transactions
    -0.09
    POSITIVE LOGITS
    Define
    0.12
    tik
    0.11
     Define
    0.11
    define
    0.11
     define
    0.11
     Compute
    0.11
    Compute
    0.10
     tik
    0.10
    solve
    0.10
     Then
    0.10
    Activations Density 0.026%

    No Known Activations