© 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. 47770
    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
    加工
    -0.08
     Rolex
    -0.08
    兑现
    -0.08
     Crafts
    -0.08
     PERF
    -0.08
    �
    -0.08
     Completion
    -0.07
    身体
    -0.07
     Inspection
    -0.07
     pains
    -0.07
    POSITIVE LOGITS
    cluster
    0.08
    ാസ
    0.08
    ijih
    0.08
     dash
    0.08
     cluster
    0.08
     മോ
    0.07
    /models
    0.07
    ijski
    0.07
     temu
    0.07
     модел
    0.07
    Activations Density 0.003%

    No Known Activations