© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20100
    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
    ted
    -0.10
    ting
    -0.10
    ivity
    -0.10
    TING
    -0.09
    ible
    -0.09
     koron
    -0.09
    ing
    -0.09
    ibility
    -0.08
    ssi
    -0.08
    ilarly
    -0.08
    POSITIVE LOGITS
    ën
    0.11
     underpin
    0.11
     philosoph
    0.10
    观点
    0.10
     doctrines
    0.10
     filoz
    0.10
     philosophers
    0.09
    体系
    0.09
    坛
    0.09
    哲
    0.09
    Activations Density 0.017%

    No Known Activations