© 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. 99233
    Prev
    Next
    INDEX
    Explanations

    Imperative verbs

    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
     Наш
    -0.08
     Discussion
    -0.08
     Indicator
    -0.08
     Launch
    -0.08
     уку
    -0.07
     Constants
    -0.07
     naš
    -0.07
     HX
    -0.07
     наше
    -0.07
     Generated
    -0.07
    POSITIVE LOGITS
    ，否则
    0.10
     reconsider
    0.10
    改善
    0.10
    Divers
    0.10
     diversify
    0.09
     સુધ
    0.09
     better
    0.09
    ぜひ
    0.09
     diversified
    0.08
     diversification
    0.08
    Activations Density 0.161%

    No Known Activations