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. 78719
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
    ishes
    -0.08
     inflammation
    -0.08
     injury
    -0.08
     violence
    -0.07
     wellness
    -0.07
    Forge
    -0.07
    INFRINGEMENT
    -0.07
    ems
    -0.07
     ISR
    -0.07
    -able
    -0.07
    POSITIVE LOGITS
    沈
    0.09
    .Users
    0.08
     taip
    0.08
     avenir
    0.08
     Submission
    0.08
     Secretario
    0.08
     નામ
    0.08
     नाम
    0.08
    .unique
    0.08
    .sys
    0.07
    Activations Density 0.000%

    No Known Activations