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. 58365
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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
    ìm
    -0.09
    िम
    -0.08
     satın
    -0.08
     برق
    -0.08
     хват
    -0.08
     езд
    -0.08
     ipp
    -0.08
     iad
    -0.08
     eléctricos
    -0.08
     Internet
    -0.08
    POSITIVE LOGITS
    MY
    0.08
    ATA
    0.07
    JA
    0.07
    onych
    0.07
    _my
    0.07
    ona
    0.07
    ZU
    0.07
    oha
    0.07
    ois
    0.07
    JD
    0.07
    Activations Density 0.000%

    No Known Activations