© 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. 21498
    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
     betrachten
    -0.09
     betracht
    -0.08
     akkor
    -0.08
     какие
    -0.08
     zeggen
    -0.08
     its
    -0.08
     complaining
    -0.08
     каких
    -0.08
    say
    -0.08
    見る
    -0.08
    POSITIVE LOGITS
     outlined
    0.14
     provided
    0.12
     outlining
    0.11
     outline
    0.10
    Outline
    0.10
     प्रदान
    0.10
    Provided
    0.10
     outlines
    0.10
     فراہم
    0.10
     sebelumnya
    0.10
    Activations Density 0.001%

    No Known Activations