© 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. 47276
    Prev
    Next
    INDEX
    Explanations

    Negative sentiments

    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
     excessively
    -0.08
     boring
    -0.08
     disastr
    -0.08
    'b
    -0.08
     bizarre
    -0.08
    igno
    -0.08
     messed
    -0.08
    -0.08
     desesper
    -0.07
     очист
    -0.07
    POSITIVE LOGITS
     légèrement
    0.10
    지만
    0.10
     hieman
    0.09
    െങ്കിലും
    0.09
     pero
    0.09
     namun
    0.09
    -free
    0.09
     ligeramente
    0.09
    하지만
    0.09
     nhưng
    0.09
    Activations Density 0.856%
    No Known Activations