Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49278
    Prev
    Next
    INDEX
    Explanations

    empty

    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
     серии
    -0.08
    .label
    -0.08
     reserves
    -0.07
     lucid
    -0.07
    .swagger
    -0.07
    лой
    -0.07
    .style
    -0.07
     rosa
    -0.07
    elsen
    -0.07
     escalate
    -0.07
    POSITIVE LOGITS
     comparison
    0.08
    ICC
    0.08
    ("--
    0.07
    origin
    0.07
     koncert
    0.07
    Comparison
    0.07
    Benef
    0.07
     resultado
    0.07
     görüş
    0.07
     recycl
    0.07
    Activations Density 0.004%

    No Known Activations