© 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. 19-RESID-POST-AA
    11. 21696
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    analog
    -0.08
    imuth
    -0.08
     analyze
    -0.07
     publicidade
    -0.07
    alyze
    -0.07
     analogous
    -0.07
     ou
    -0.07
     optics
    -0.07
     alebo
    -0.07
    ुग
    -0.07
    POSITIVE LOGITS
    *self
    0.09
    _色
    0.09
    'ireo
    0.08
    زالة
    0.08
    _免费
    0.08
    .Б
    0.08
    һына
    0.08
    玖玖
    0.08
    "ו
    0.08
     чтоб
    0.08
    Activations Density 0.004%

    No Known Activations