© 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. 21956
    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
     also
    -0.10
     furthermore
    -0.10
     juga
    -0.09
    enness
    -0.09
     myös
    -0.09
    areness
    -0.09
     Furthermore
    -0.09
     även
    -0.09
    ooks
    -0.09
     Moreover
    -0.09
    POSITIVE LOGITS
     formatted
    0.15
     finalized
    0.13
    字符串
    0.12
     markdown
    0.12
     pasted
    0.12
    文本
    0.11
     plaintext
    0.11
     texto
    0.11
     мәт
    0.11
     únicamente
    0.11
    Activations Density 0.056%

    No Known Activations