© 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. 23-RESID-POST-AA
    11. 5441
    Prev
    Next
    INDEX
    Explanations

    Feudal dues and rent

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =end
    -0.09
    Tags
    -0.08
    藏宝
    -0.08
    ately
    -0.08
    (end
    -0.08
    (keyword
    -0.08
    [end
    -0.08
     karm
    -0.08
     Tags
    -0.08
    824
    -0.08
    POSITIVE LOGITS
     poll
    0.10
     sc
    0.09
     cor
    0.09
     tradi
    0.09
     Sc
    0.09
     servizi
    0.09
     homage
    0.09
     traditional
    0.08
     copy
    0.08
     dix
    0.08
    Activations Density 0.002%

    No Known Activations