© 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. 19-RESID-POST-AA
    11. 102559
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    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
    continuous
    -0.09
     상당
    -0.09
     ganska
    -0.08
     continuous
    -0.08
     både
    -0.08
     весьма
    -0.08
     많은
    -0.08
    大量
    -0.08
     relativement
    -0.08
     largas
    -0.08
    POSITIVE LOGITS
     few
    0.13
     quelques
    0.12
     vài
    0.11
     chút
    0.10
     kilka
    0.10
     briefly
    0.10
     couple
    0.10
     birkaç
    0.10
     paar
    0.10
     wenige
    0.09
    Activations Density 0.006%

    No Known Activations