© 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. 11-RESID-POST-AA
    11. 70597
    Prev
    Next
    INDEX
    Explanations

    adolescent sleep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赔率
    -0.09
    krips
    -0.08
     XML
    -0.08
     buoy
    -0.08
     pérdidas
    -0.08
    .restore
    -0.08
     XPath
    -0.08
     '"'
    -0.08
    赔
    -0.07
     Brü
    -0.07
    POSITIVE LOGITS
     shifting
    0.10
    shift
    0.10
    Shift
    0.10
     nights
    0.09
     shift
    0.09
     shifted
    0.09
    _shift
    0.09
    SHIFT
    0.09
    foobar
    0.08
    _SHIFT
    0.08
    Activations Density 0.006%

    No Known Activations