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. 11884
    Prev
    Next
    INDEX
    Explanations

    journeys to save world

    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
     Konto
    -0.08
     gait
    -0.08
     personalidad
    -0.08
     Enrollment
    -0.08
     fotografía
    -0.07
     haut
    -0.07
     personnalité
    -0.07
    开户
    -0.07
     privilégi
    -0.07
     physique
    -0.07
    POSITIVE LOGITS
     threatens
    0.11
     unrest
    0.11
    危
    0.11
     devast
    0.11
     devastation
    0.11
     emergencies
    0.11
     संकट
    0.10
     restoration
    0.10
     threats
    0.10
     disasters
    0.10
    Activations Density 0.038%

    No Known Activations