© 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. 68276
    Prev
    Next
    INDEX
    Explanations

    纳

    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
     ?"
    -0.07
     destroy
    -0.07
     Ayr
    -0.07
     enj
    -0.07
     onsite
    -0.07
    άρ
    -0.07
    997
    -0.07
     draa
    -0.07
     Harriet
    -0.07
     ?",
    -0.07
    POSITIVE LOGITS
     baten
    0.08
    _kwargs
    0.08
     způsob
    0.08
    식
    0.07
    /map
    0.07
    িকার
    0.07
    /model
    0.07
    _tail
    0.07
     సంగ
    0.07
    ોદ
    0.07
    Activations Density 0.001%

    No Known Activations