© 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. 19660
    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
    -plus
    -0.09
    Here
    -0.09
    ，实现
    -0.08
    Where
    -0.08
     ഇവിടെ
    -0.08
    Plus
    -0.08
    ここ
    -0.08
    ات
    -0.08
    あります
    -0.08
     যেখানে
    -0.08
    POSITIVE LOGITS
     fazê
    0.16
    首先
    0.12
     반드시
    0.11
     first
    0.11
     उसमें
    0.11
     hacerlo
    0.11
     eerst
    0.11
     అది
    0.11
     उससे
    0.10
     zároveň
    0.10
    Activations Density 0.054%

    No Known Activations