© 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. 202
    Prev
    Next
    INDEX
    Explanations

    orchid

    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
     Grap
    -0.08
    IRONMENT
    -0.08
    umulative
    -0.08
     населения
    -0.08
     escal
    -0.08
    hte
    -0.07
     cumulative
    -0.07
     Stalin
    -0.07
     collectiv
    -0.07
    fo
    -0.07
    POSITIVE LOGITS
     elegance
    0.10
     orchids
    0.09
     elegant
    0.09
     chiếc
    0.09
    般
    0.08
     شان
    0.08
     raff
    0.08
     sé
    0.08
     petals
    0.08
     Elegant
    0.08
    Activations Density 0.005%

    No Known Activations