© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 589
    Prev
    Next
    INDEX
    Explanations

    B

    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
     Mang
    -0.09
     Surgery
    -0.09
     proseso
    -0.08
     Cardi
    -0.08
     Crit
    -0.08
     Principles
    -0.08
    ్త
    -0.07
     Claudia
    -0.07
     parto
    -0.07
     Indicator
    -0.07
    POSITIVE LOGITS
     brush
    0.09
     وعد
    0.08
    ))
    ↵
    ↵
    0.08
     lifetime
    0.08
     brushes
    0.08
     جاه
    0.08
     обладают
    0.08
     bafite
    0.08
    ])
    ↵
    0.08
    ורים
    0.07
    Activations Density 0.000%

    No Known Activations