© 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. 19758
    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
    Connections
    -0.09
     ಸಂಪರ್ಕ
    -0.08
    ್ಸ್
    -0.08
    iesa
    -0.08
    ಫ
    -0.08
    oted
    -0.07
     connections
    -0.07
    ೇಷ
    -0.07
     then
    -0.07
     padd
    -0.07
    POSITIVE LOGITS
    ుకొని
    0.10
    起来
    0.09
     tavalla
    0.09
    ված
    0.09
    таи
    0.09
     നൽക
    0.09
     प्रदान
    0.09
    的方法
    0.09
     हुए
    0.09
    的新
    0.09
    Activations Density 0.005%

    No Known Activations