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. 42103
    Prev
    Next
    INDEX
    Explanations

    Pending

    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
    FDB
    -0.08
    .Form
    -0.07
     attracted
    -0.07
    -line
    -0.07
    ورد
    -0.07
    tributions
    -0.07
     nightly
    -0.07
     принос
    -0.07
    ñe
    -0.07
     anatom
    -0.07
    POSITIVE LOGITS
    手续
    0.08
     Zo
    0.08
     gezamenlijk
    0.07
    sizeof
    0.07
    aunch
    0.07
     kartu
    0.07
     zos
    0.07
    Samen
    0.07
    ("./
    0.07
     клап
    0.07
    Activations Density 0.001%

    No Known Activations