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. 12223
    Prev
    Next
    INDEX
    Explanations

    Whole or large

    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
     begs
    -0.08
     служб
    -0.07
     Bits
    -0.07
    liest
    -0.07
     Tras
    -0.07
    ekl
    -0.07
     Set
    -0.07
     tempus
    -0.07
     Validator
    -0.07
     (**
    -0.07
    POSITIVE LOGITS
    来说
    0.13
    而言
    0.12
    认为
    0.11
    യായി
    0.10
    沿
    0.09
    तः
    0.08
    较
    0.08
     대부분
    0.08
    적으로
    0.08
    十分
    0.08
    Activations Density 0.032%

    No Known Activations