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. 444
    Prev
    Next
    INDEX
    Explanations

    Permutations and combinations

    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
     Unified
    -0.08
    Unified
    -0.07
    sync
    -0.07
     yhte
    -0.07
    -0.07
    sent
    -0.07
    ticks
    -0.06
    ીવ
    -0.06
     unified
    -0.06
    tfoot
    -0.06
    POSITIVE LOGITS
     باقي
    0.12
     surrounding
    0.12
     остальных
    0.12
     остальные
    0.12
     дальше
    0.12
     الأخرى
    0.11
     subsequently
    0.11
     afterward
    0.11
     afterwards
    0.11
    _remaining
    0.11
    Activations Density 0.057%

    No Known Activations