© 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. 21553
    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
     wellicht
    -0.10
     misschien
    -0.10
     դուք
    -0.10
     Ձեր
    -0.09
     Դուք
    -0.09
     თქვენს
    -0.09
     ويتم
    -0.09
    �
    -0.09
     måske
    -0.09
    ​ក្នុង
    -0.09
    POSITIVE LOGITS
    片
    0.09
    瞬
    0.09
     кус
    0.09
     Ге
    0.08
    장의
    0.08
    场
    0.08
     τό
    0.08
     ತು
    0.08
    สบ
    0.08
     poema
    0.08
    Activations Density 0.004%

    No Known Activations