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. 12270
    Prev
    Next
    INDEX
    Explanations

    ASIA A

    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
    Celebr
    -0.09
     celebrations
    -0.09
     �
    -0.09
     celebration
    -0.08
     Rumah
    -0.08
     notices
    -0.08
     hogares
    -0.08
     Sty
    -0.08
     domést
    -0.08
     Celebration
    -0.08
    POSITIVE LOGITS
    态
    0.09
     retro
    0.08
    认证
    0.08
     Retro
    0.08
     retrospect
    0.08
     posture
    0.08
    评
    0.08
     grade
    0.08
     therapeutic
    0.07
    Worst
    0.07
    Activations Density 0.001%

    No Known Activations