© 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 EvalsExportsinterp-engineNEWAPI 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. 51715
    Prev
    Next
    INDEX
    Explanations

    弹

    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
    58
    -0.08
     botanical
    -0.08
     eleg
    -0.07
    there
    -0.07
    umberland
    -0.07
     mudd
    -0.07
    cemos
    -0.07
    δά
    -0.07
     familiares
    -0.07
    rine
    -0.07
    POSITIVE LOGITS
    性
    0.13
    幕
    0.13
    窗
    0.12
    (const
    0.12
     const
    0.11
    const
    0.11
    薬
    0.11
    药
    0.10
    奏
    0.10
    性的
    0.10
    Activations Density 0.002%

    No Known Activations