© 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. 19902
    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
     પ્રથમ
    -0.09
     પહેલા
    -0.08
     valam
    -0.08
     प्रथम
    -0.08
    ただ
    -0.08
     पहली
    -0.08
     zunächst
    -0.08
     primero
    -0.08
     પહેલ
    -0.08
     already
    -0.08
    POSITIVE LOGITS
     worrying
    0.20
     worry
    0.19
     preocupar
    0.18
     preocupação
    0.17
     concerned
    0.16
     precise
    0.16
     worries
    0.15
     concern
    0.15
     strict
    0.15
     rigorous
    0.15
    Activations Density 0.030%

    No Known Activations