© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 18738
    Prev
    Next
    INDEX
    Explanations

    man

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    And
    -0.08
     comes
    -0.08
    Bit
    -0.08
    'ap
    -0.08
    The
    -0.08
    verm
    -0.08
    ë
    -0.08
     packing
    -0.07
    ''
    -0.07
    and
    -0.07
    POSITIVE LOGITS
    .):
    0.09
     большей
    0.08
     реи
    0.08
     имен
    0.08
     {};↵↵
    0.08
     {});↵
    0.08
     объект
    0.08
    khiqizo
    0.08
     retval
    0.08
     参数
    0.08
    Activations Density 0.000%

    No Known Activations