© 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. 21837
    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
    andukanye
    -0.09
     Matcher
    -0.08
    سطس
    -0.08
     birbir
    -0.08
    ewise
    -0.08
     aunque
    -0.08
     بلکه
    -0.08
     Mobile
    -0.08
    Matchers
    -0.07
     separ
    -0.07
    POSITIVE LOGITS
    …,
    0.09
     ಊ
    0.09
    -normal
    0.08
    ...,
    0.08
    将在
    0.08
     наблю
    0.08
    ೌ
    0.08
    ಲ್
    0.08
    ��
    0.07
    -bodied
    0.07
    Activations Density 0.000%

    No Known Activations