Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77214
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
     preservatives
    -0.08
    鞋
    -0.07
    tracker
    -0.07
    ercise
    -0.07
    mode
    -0.07
     comienzo
    -0.07
    meen
    -0.07
    ابس
    -0.07
     silly
    -0.07
    יפול
    -0.07
    POSITIVE LOGITS
     testimon
    0.10
     endorsements
    0.10
     témoign
    0.10
     endors
    0.10
     unanimous
    0.10
    意见
    0.09
     affirme
    0.09
     endorse
    0.09
     reputable
    0.09
     disagreement
    0.09
    Activations Density 0.158%

    No Known Activations