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. 48972
    Prev
    Next
    INDEX
    Explanations

    |

    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
     ".
    -0.07
     writable
    -0.07
    demo
    -0.07
    多少
    -0.07
     reclaim
    -0.07
    510
    -0.07
     ਵੀ
    -0.07
     `.
    -0.07
     reis
    -0.07
     simplest
    -0.07
    POSITIVE LOGITS
    _constraints
    0.08
    빙
    0.07
     Fiona
    0.07
    _flip
    0.07
     abo
    0.07
    어서
    0.07
    妮
    0.07
    _other
    0.07
    adil
    0.07
    _MEMORY
    0.07
    Activations Density 0.014%

    No Known Activations