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. 65295
    Prev
    Next
    INDEX
    Explanations

    username/ID

    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
    男女
    -0.07
    _LEVEL
    -0.07
     Education
    -0.07
     Vegas
    -0.07
     Pong
    -0.07
     parliament
    -0.07
     NGOs
    -0.07
     Cali
    -0.07
     Vip
    -0.07
     margem
    -0.06
    POSITIVE LOGITS
     elusive
    0.10
     forgotten
    0.10
     difficulties
    0.09
     भूल
    0.09
     kennen
    0.09
     трудно
    0.09
     bekom
    0.09
     moeilijk
    0.09
     Forgotten
    0.09
     difficultés
    0.09
    Activations Density 0.008%

    No Known Activations