© 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. 26575
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ovski
    -0.08
     Çok
    -0.08
     Hebrews
    -0.08
     Russian
    -0.08
     sosai
    -0.07
     уни
    -0.07
     Fitzgerald
    -0.07
    Russian
    -0.07
     অস্ত
    -0.07
     заканч
    -0.07
    POSITIVE LOGITS
    环保
    0.17
     Greenpeace
    0.15
     activism
    0.15
     renewable
    0.14
     compost
    0.14
     environmentally
    0.14
     Renewable
    0.14
     Compost
    0.13
    Eco
    0.13
     pollut
    0.13
    Activations Density 0.145%

    No Known Activations