© 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. 22283
    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
     customization
    -0.09
     customize
    -0.09
    .validation
    -0.09
     bilingual
    -0.09
     Validation
    -0.08
     CRUD
    -0.08
     customizable
    -0.08
    Validation
    -0.08
     validation
    -0.08
    Customization
    -0.08
    POSITIVE LOGITS
     speculative
    0.27
     speculation
    0.21
     speculate
    0.20
     imaginative
    0.20
     futuristic
    0.16
     plausible
    0.16
     theoretical
    0.16
     spé
    0.16
     sci
    0.16
     фанта
    0.16
    Activations Density 0.049%

    No Known Activations