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. 29962
    Prev
    Next
    INDEX
    Explanations

    palette

    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
    try
    -0.09
     ilíc
    -0.08
     nghị
    -0.08
    ặn
    -0.08
    νή
    -0.08
     cryptocurrency
    -0.08
     tài
    -0.08
     Inde
    -0.08
     Fool
    -0.07
    .try
    -0.07
    POSITIVE LOGITS
     bright
    0.09
     হৈ
    0.08
     environment
    0.07
     ظروف
    0.07
     couleurs
    0.07
     colores
    0.07
    -Hol
    0.07
     brillante
    0.07
     wing
    0.07
     atmosphere
    0.07
    Activations Density 0.006%

    No Known Activations