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. 15-RESID-POST-AA
    6. 18962
    Prev
    Next
    INDEX
    Explanations

    |

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perhaps
    -0.08
     probably
    -0.08
     both
    -0.08
     lait
    -0.08
     possibly
    -0.08
     that
    -0.08
    ?",↵
    -0.07
     lots
    -0.07
     whether
    -0.07
     ongoing
    -0.07
    POSITIVE LOGITS
    })↵↵//
    0.09
    ()))↵↵
    0.08
    ))↵↵↵
    0.08
    ))↵↵
    0.08
    *)↵↵
    0.08
    })↵↵
    0.08
    --------------↵↵
    0.08
    _SUPPORTED
    0.08
    });↵↵
    0.08
    355
    0.08
    Activations Density 0.031%

    No Known Activations