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. 59267
    Prev
    Next
    INDEX
    Explanations

    R

    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
     �
    -0.10
     �
    -0.08
     Spannung
    -0.08
    ോഷ
    -0.08
     recompensa
    -0.08
    ഴ
    -0.08
     glimps
    -0.08
    ിട
    -0.08
    ไม้
    -0.08
    护
    -0.07
    POSITIVE LOGITS
     zeit
    0.08
    Except
    0.08
     bif
    0.08
     hel
    0.08
     sep
    0.07
    中特
    0.07
    (the
    0.07
    .mk
    0.07
    Dam
    0.07
     redux
    0.07
    Activations Density 0.016%

    No Known Activations