© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91528
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferrovi
    -0.08
     дил
    -0.08
     �
    -0.08
     المياه
    -0.07
     empirical
    -0.07
     εται
    -0.07
     brokerage
    -0.07
     logistics
    -0.07
     dealership
    -0.07
     parques
    -0.07
    POSITIVE LOGITS
    med
    0.08
    ěž
    0.08
    &,
    0.08
    inf
    0.07
    usuarios
    0.07
     Finds
    0.07
     CTRL
    0.07
     Consequently
    0.07
    ji
    0.07
     tố
    0.07
    Activations Density 0.000%

    No Known Activations