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. 111648
    Prev
    Next
    INDEX
    Explanations

    都

    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
     کاری
    -0.08
     lest
    -0.08
     того
    -0.07
    adecimal
    -0.07
    ार्थ
    -0.07
     accred
    -0.07
    .contrib
    -0.07
     таго
    -0.07
     چل
    -0.07
     bok
    -0.07
    POSITIVE LOGITS
    0.08
     wasted
    0.08
     gating
    0.08
     conveniently
    0.07
    体现
    0.07
     �
    0.07
     ആയ
    0.07
     Pase
    0.07
    严
    0.07
     Yan
    0.07
    Activations Density 0.004%

    No Known Activations