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. 98530
    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
     Penny
    -0.08
     Username
    -0.08
    igans
    -0.08
     penny
    -0.08
     pł
    -0.08
     Candy
    -0.08
    	yield
    -0.08
     రె
    -0.07
     אַ
    -0.07
    ғи
    -0.07
    POSITIVE LOGITS
    Applicable
    0.08
     vasta
    0.07
     provincial
    0.07
    ONA
    0.07
     Mazda
    0.07
    wide
    0.07
     Olympic
    0.07
     jusqu
    0.07
     manufacturers
    0.07
    519
    0.07
    Activations Density 0.021%

    No Known Activations