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. 129707
    Prev
    Next
    INDEX
    Explanations

    coup

    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
     Zheng
    -0.08
     nhu
    -0.07
     Li
    -0.07
     Guerrero
    -0.07
    ολ
    -0.07
    igator
    -0.07
    تين
    -0.07
    ute
    -0.07
     catt
    -0.07
    ของ
    -0.07
    POSITIVE LOGITS
     overthrow
    0.13
     смен
    0.09
     заменить
    0.09
     বদ
    0.09
     reempl
    0.09
     takeover
    0.09
    Replacement
    0.08
     destabil
    0.08
     dereg
    0.08
    ISTRATION
    0.08
    Activations Density 0.013%

    No Known Activations