© 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. 21772
    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
    릴
    -0.09
    künd
    -0.09
    purpose
    -0.08
    cada
    -0.08
    gust
    -0.08
    iz
    -0.08
    entscheid
    -0.08
    wonder
    -0.08
    intend
    -0.08
    queries
    -0.08
    POSITIVE LOGITS
     combining
    0.15
     Combining
    0.14
    Putting
    0.12
     Combine
    0.12
    Combine
    0.12
    Comb
    0.12
     ترکی
    0.11
     combines
    0.10
    .Combine
    0.10
    .combine
    0.10
    Activations Density 0.017%

    No Known Activations