© 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. 20197
    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
    ♀♀♀♀
    -0.12
    <|reserved_200014|>
    -0.12
    -0.12
    -0.12
    ♀♀♀♀♀♀
    -0.12
    ♀♀♀
    -0.12
    -0.11
    �&&
    -0.11
    ข้อความเต็ม
    -0.11
    SUPERHOST
    -0.11
    POSITIVE LOGITS
     numbering
    0.12
     definition
    0.11
     can
    0.11
     cannot
    0.10
     definitions
    0.10
     may
    0.10
     can't
    0.10
     numbers
    0.10
     could
    0.10
     యొక్క
    0.10
    Activations Density 0.111%
    No Known Activations