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. 90562
    Prev
    Next
    INDEX
    Explanations

    software design patterns

    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
     rgb
    -0.08
     destiny
    -0.08
     lyrics
    -0.08
     Arial
    -0.08
     liy
    -0.08
     chất
    -0.08
     mosquitoes
    -0.08
    hibition
    -0.08
     colored
    -0.08
     lh
    -0.08
    POSITIVE LOGITS
     Patterns
    0.13
    _patterns
    0.12
     pitfalls
    0.12
    Patterns
    0.12
     patterns
    0.12
     patrones
    0.11
    patterns
    0.11
     recurring
    0.10
     épr
    0.10
     motifs
    0.10
    Activations Density 0.031%

    No Known Activations