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. 29831
    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
     imper
    -0.08
    ்ச
    -0.08
    �
    -0.08
     lum
    -0.08
     wisely
    -0.07
     mist
    -0.07
    ாவில்
    -0.07
    ollo
    -0.07
     venen
    -0.07
    lev
    -0.07
    POSITIVE LOGITS
    vq
    0.09
     Gross
    0.08
     Sund
    0.08
     Richard
    0.08
     Major
    0.08
     �
    0.08
     Dar
    0.07
    ૈય
    0.07
     verle
    0.07
     അട
    0.07
    Activations Density 0.037%

    No Known Activations