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. 43576
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    ammelt
    -0.08
    �
    -0.08
     handing
    -0.07
    deadline
    -0.07
    牢
    -0.07
    activo
    -0.07
     British
    -0.07
     gezondheid
    -0.07
    Deadline
    -0.07
    ুক
    -0.07
    POSITIVE LOGITS
     likewise
    0.11
     hingegen
    0.10
    こちら
    0.10
     ebenfalls
    0.10
     тоже
    0.09
     itd
    0.09
    則
    0.08
     Athena
    0.08
     invece
    0.08
     similarly
    0.08
    Activations Density 0.058%

    No Known Activations