© 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. 20084
    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
    ฎ
    -0.09
     uniformly
    -0.08
    адает
    -0.08
    úl
    -0.08
    หรือ
    -0.07
    าญ
    -0.07
     эффективно
    -0.07
    ้าที่
    -0.07
    เซีย
    -0.07
    การเดิมพัน
    -0.07
    POSITIVE LOGITS
    kulunkulu
    0.16
    iversal
    0.15
    iversity
    0.15
    forgettable
    0.14
    precedented
    0.13
    certainty
    0.13
    ited
    0.12
    usual
    0.12
    specified
    0.12
    IVERS
    0.11
    Activations Density 0.014%

    No Known Activations