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. 23880
    Prev
    Next
    INDEX
    Explanations

    角

    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
     uuid
    -0.08
    ylum
    -0.07
     menu
    -0.07
     random
    -0.07
     rnd
    -0.07
     requ
    -0.07
     repr
    -0.07
     lengthy
    -0.07
    _GLOBAL
    -0.07
     novel
    -0.07
    POSITIVE LOGITS
    地区
    0.09
    �
    0.08
     ecosystems
    0.08
     comércio
    0.08
     మండ
    0.08
    وافق
    0.08
    0.08
     Wellness
    0.08
     Wear
    0.07
     Jewel
    0.07
    Activations Density 0.005%

    No Known Activations