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. 120275
    Prev
    Next
    INDEX
    Explanations

    inclusive

    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
    oppen
    -0.09
    512
    -0.09
    128
    -0.08
     addiction
    -0.08
    metry
    -0.08
    omach
    -0.08
    540
    -0.08
    440
    -0.07
    480
    -0.07
    430
    -0.07
    POSITIVE LOGITS
     periodo
    0.09
     período
    0.08
    -period
    0.08
    _period
    0.08
    _PERIOD
    0.08
    विद्यालय
    0.07
    렬
    0.07
    Periods
    0.07
     pickup
    0.07
    .tiles
    0.07
    Activations Density 0.014%

    No Known Activations