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. 29858
    Prev
    Next
    INDEX
    Explanations

    mathematics equations

    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
     asesinato
    -0.08
     стадии
    -0.08
     stages
    -0.08
     internships
    -0.08
     deterioration
    -0.07
     temptation
    -0.07
     შემდეგ
    -0.07
     onge
    -0.07
    	desc
    -0.07
    .addr
    -0.07
    POSITIVE LOGITS
     Odd
    0.09
     subset
    0.09
     Walsh
    0.08
    Odd
    0.08
     odd
    0.08
     aquellas
    0.08
    _indices
    0.08
     }
    ↵
    0.08
    -wise
    0.08
     sépar
    0.08
    Activations Density 0.020%

    No Known Activations