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. 268
    Prev
    Next
    INDEX
    Explanations

    sealing dough in recipes

    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
    .parallel
    -0.09
    .sem
    -0.08
    .credentials
    -0.08
    ohner
    -0.08
    .single
    -0.08
    .first
    -0.08
    ুন
    -0.08
    .currency
    -0.08
    (OS
    -0.08
     Credentials
    -0.08
    POSITIVE LOGITS
    Shape
    0.10
     shape
    0.09
     shapes
    0.09
     Shape
    0.09
    shape
    0.08
     endings
    0.08
     shaped
    0.08
    -shaped
    0.08
    _shape
    0.08
     cusp
    0.08
    Activations Density 0.011%

    No Known Activations