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. 58829
    Prev
    Next
    INDEX
    Explanations

    antimicrobial

    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
    oral
    -0.08
     confused
    -0.08
    河
    -0.08
     confusing
    -0.08
     отзы
    -0.08
     trov
    -0.07
     عب
    -0.07
     Tritur
    -0.07
     devotees
    -0.07
     devotion
    -0.07
    POSITIVE LOGITS
     antimicrobial
    0.13
     antiviral
    0.11
     antibacterial
    0.11
     coatings
    0.10
     bacteria
    0.10
     langleb
    0.09
     antivirus
    0.09
     disinfect
    0.09
     microbes
    0.09
    -virus
    0.09
    Activations Density 0.008%

    No Known Activations