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. 114011
    Prev
    Next
    INDEX
    Explanations

    leg

    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
    应该
    -0.08
    discord
    -0.08
     长
    -0.08
    website
    -0.08
    什么时候
    -0.08
    dao
    -0.08
    osite
    -0.08
     praat
    -0.08
     انا
    -0.08
    ခ်
    -0.08
    POSITIVE LOGITS
     Texas
    0.09
     collapse
    0.08
     suscept
    0.08
    .coll
    0.08
     collapsed
    0.08
    Sus
    0.08
     Sus
    0.08
     stolen
    0.07
     manner
    0.07
     Tres
    0.07
    Activations Density 0.001%

    No Known Activations