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. 111611
    Prev
    Next
    INDEX
    Explanations

    name

    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
     phải
    -0.08
    遂
    -0.08
    依法
    -0.08
     Devil
    -0.08
    我要
    -0.07
     iwu
    -0.07
    (dd
    -0.07
    不得
    -0.07
     obsessive
    -0.07
     auster
    -0.07
    POSITIVE LOGITS
     personalized
    0.13
     personalization
    0.13
     Personalized
    0.12
     tailoring
    0.11
     personalize
    0.11
     greetings
    0.10
    Greeting
    0.10
    utente
    0.10
    unsubscribe
    0.10
     personnalisé
    0.10
    Activations Density 0.010%

    No Known Activations