© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54888
    Prev
    Next
    INDEX
    Explanations

    Positive emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amiliar
    -0.08
    .segment
    -0.07
    ó
    -0.07
    Genesis
    -0.07
     stated
    -0.07
     בכך
    -0.07
    Next
    -0.07
    Broadcast
    -0.07
     broadcast
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     conviction
    0.10
     optimism
    0.09
     enthous
    0.09
     jungle
    0.09
     Té
    0.08
    лишком
    0.08
     sheer
    0.08
     produkt
    0.08
     vigor
    0.08
     riches
    0.08
    Activations Density 0.056%

    No Known Activations