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. 60476
    Prev
    Next
    INDEX
    Explanations

    woman

    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
     Cornell
    -0.08
    Ast
    -0.08
     نامه
    -0.07
     bedeutet
    -0.07
     commons
    -0.07
    ئر
    -0.07
    (cert
    -0.07
    Ho
    -0.07
    ட்டி
    -0.07
     CFR
    -0.07
    POSITIVE LOGITS
     sigh
    0.08
     anguish
    0.07
     accuse
    0.07
    acher
    0.07
    에게
    0.07
    luv
    0.07
    开心
    0.07
     embarrassment
    0.07
     gladly
    0.07
     sincerely
    0.07
    Activations Density 0.005%

    No Known Activations