© 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 EvalsExportsinterp-engineNEWAPI 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. 21997
    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
    手机在线
    -0.09
    falen
    -0.09
    价值
    -0.09
    իւ
    -0.09
    ailoga
    -0.09
     ngaahi
    -0.09
    怎么领
    -0.09
     valeur
    -0.09
     verloor
    -0.09
    腾讯分分彩
    -0.09
    POSITIVE LOGITS
    (Level
    0.13
    led
    0.12
    .SEVERE
    0.11
    =logging
    0.10
    .Level
    0.10
    (level
    0.10
    -wise
    0.10
    .Detail
    0.09
    -level
    0.09
     détail
    0.09
    Activations Density 0.035%

    No Known Activations