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. 65504
    Prev
    Next
    INDEX
    Explanations

    API

    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
     scrambled
    -0.08
    Lincoln
    -0.08
     Lincoln
    -0.08
    Dispatcher
    -0.08
     Irish
    -0.08
    Cipher
    -0.08
    Hasher
    -0.08
     Pere
    -0.07
    _cipher
    -0.07
    ????????
    -0.07
    POSITIVE LOGITS
    /swagger
    0.12
    .swagger
    0.12
     документа
    0.10
     documentation
    0.10
     springfox
    0.10
    .Description
    0.10
    .description
    0.10
     swagger
    0.10
     Swagger
    0.10
    (description
    0.10
    Activations Density 0.003%

    No Known Activations