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. 102910
    Prev
    Next
    INDEX
    Explanations

    line

    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
    'image
    -0.08
    지노
    -0.08
     Premier
    -0.08
     Vinyl
    -0.07
     фен
    -0.07
     aang
    -0.07
     hela
    -0.07
    /add
    -0.07
     indicators
    -0.07
    企
    -0.07
    POSITIVE LOGITS
    DETAIL
    0.10
     রাখা
    0.08
    Example
    0.08
    .*;
    ↵
    ↵
    0.08
     tertentu
    0.08
    িমান
    0.08
    TRACE
    0.07
     rotates
    0.07
     rotating
    0.07
    }$/
    0.07
    Activations Density 0.012%

    No Known Activations