© 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. 22368
    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
     יד
    -0.08
     modern
    -0.08
     আধ
    -0.08
    Collectors
    -0.08
     spying
    -0.08
    istoire
    -0.08
    现代
    -0.07
     মাঠ
    -0.07
     brainstorming
    -0.07
     responsabilités
    -0.07
    POSITIVE LOGITS
     sensational
    0.10
     nouve
    0.09
     emotionally
    0.09
     extremes
    0.09
     aquello
    0.09
     novelty
    0.09
     nära
    0.09
     nabij
    0.09
     upravo
    0.09
    重复
    0.08
    Activations Density 0.005%

    No Known Activations