© 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. 22370
    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
     linestyle
    -0.09
    .frequency
    -0.07
    imator
    -0.07
    angered
    -0.07
     настро
    -0.07
     frequencies
    -0.07
    atini
    -0.07
    imbledon
    -0.07
     filenames
    -0.07
    -frequency
    -0.07
    POSITIVE LOGITS
    面积
    0.16
     مساحة
    0.16
     sqft
    0.15
    ㎡
    0.14
     площади
    0.14
     площадь
    0.13
     площ
    0.13
     Fläche
    0.13
     sprawling
    0.13
     площад
    0.13
    Activations Density 0.022%

    No Known Activations