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. 101322
    Prev
    Next
    INDEX
    Explanations

    bacterial

    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
     regret
    -0.10
     Implementation
    -0.09
     regrets
    -0.08
    staff
    -0.08
     abst
    -0.08
    mare
    -0.08
    workspace
    -0.08
     drawers
    -0.08
     elbow
    -0.08
     refr
    -0.08
    POSITIVE LOGITS
     pathogens
    0.11
     pathogen
    0.11
     pathogenic
    0.10
    ڑے
    0.09
     endot
    0.09
     fungi
    0.09
    產品
    0.09
     bacteria
    0.09
     contaminants
    0.08
     aggregates
    0.08
    Activations Density 0.006%

    No Known Activations