Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11786
    Prev
    Next
    INDEX
    Explanations

    instructions for software/apps

    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
    Annotated
    -0.08
    acio
    -0.07
     aportar
    -0.07
    001
    -0.07
     formation
    -0.07
     seize
    -0.07
    Applying
    -0.07
     incorporación
    -0.07
    _simple
    -0.07
    拼
    -0.07
    POSITIVE LOGITS
     настройки
    0.11
     preferencias
    0.11
     preferences
    0.10
     настрой
    0.10
    instellungen
    0.10
     Einstellungen
    0.10
     настро
    0.10
     ingesteld
    0.10
     إعداد
    0.09
     préfér
    0.09
    Activations Density 0.041%

    No Known Activations