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. 9105
    Prev
    Next
    INDEX
    Explanations

    Behaviour

    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
     nearly
    -0.08
    েনে
    -0.07
     بك
    -0.07
    いや
    -0.07
    Jacob
    -0.07
     computation
    -0.07
    almost
    -0.07
    /backend
    -0.07
    _unc
    -0.07
    -poly
    -0.07
    POSITIVE LOGITS
     somet
    0.08
     Ass
    0.08
     }));↵↵
    0.08
     }));↵
    0.08
     ")");↵
    0.08
    ")]
    ↵
    0.08
     предназнач
    0.08
     }]↵
    0.08
     IUser
    0.08
     બન
    0.07
    Activations Density 0.002%

    No Known Activations