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. 102634
    Prev
    Next
    INDEX
    Explanations

    overcome

    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
     parl
    -0.08
     sigh
    -0.08
     rod
    -0.08
     omin
    -0.08
    sit
    -0.08
    تان
    -0.07
    MG
    -0.07
    署
    -0.07
     Accredited
    -0.07
     Hathaway
    -0.07
    POSITIVE LOGITS
     hurdles
    0.11
     barriers
    0.11
     obstacles
    0.11
     overcome
    0.10
     hurdle
    0.09
     deficiencies
    0.09
     adversity
    0.09
     barrier
    0.09
     overcoming
    0.09
    不了
    0.09
    Activations Density 0.011%

    No Known Activations