© 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. 22068
    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
    .export
    -0.08
     resultant
    -0.08
    これは
    -0.08
     representan
    -0.07
     conocido
    -0.07
     myriad
    -0.07
     matriz
    -0.07
    ndata
    -0.07
    679
    -0.07
    关键
    -0.07
    POSITIVE LOGITS
     ("
    0.14
     acknowledging
    0.13
     asking
    0.13
     (“
    0.12
    하면서
    0.12
    하며
    0.12
     politely
    0.12
    ，同时
    0.12
     encouraging
    0.11
    "I'm
    0.11
    Activations Density 0.042%

    No Known Activations