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. 48529
    Prev
    Next
    INDEX
    Explanations

    form

    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
     ప్రేక్షక
    -0.08
     audience
    -0.08
     timers
    -0.08
    يص
    -0.08
     visant
    -0.08
     नंबर
    -0.08
     président
    -0.08
    udience
    -0.08
    лиси
    -0.08
     dédiée
    -0.08
    POSITIVE LOGITS
     peroxide
    0.10
     bonds
    0.09
    oxide
    0.09
     bond
    0.09
     Oxygen
    0.09
     formation
    0.09
    氧
    0.08
    forming
    0.08
     Bonds
    0.08
    bond
    0.08
    Activations Density 0.006%

    No Known Activations