© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 20707
    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
    _日本
    -0.11
    +[
    -0.09
    -init
    -0.09
    008
    -0.09
    -а
    -0.09
    ающих
    -0.08
    _init
    -0.08
    -ahụ
    -0.08
    continence
    -0.08
    -日本
    -0.08
    POSITIVE LOGITS
    G
    0.13
    D
    0.11
    K
    0.11
    M
    0.11
    F
    0.11
    GS
    0.10
    MK
    0.10
    S
    0.10
    k
    0.10
    J
    0.10
    Activations Density 0.005%

    No Known Activations