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. 43690
    Prev
    Next
    INDEX
    Explanations

    infections

    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
     greetings
    -0.08
     treaties
    -0.08
     lifestyles
    -0.08
     saludo
    -0.08
     Gespr
    -0.08
     Lifestyle
    -0.08
     καλ
    -0.08
     lifestyle
    -0.07
    Greetings
    -0.07
     cuestion
    -0.07
    POSITIVE LOGITS
     postoperative
    0.11
     malpractice
    0.09
     EFI
    0.09
     accreditation
    0.09
     NSF
    0.08
     NIV
    0.08
     spoil
    0.08
     postop
    0.08
     ROB
    0.08
     pós
    0.08
    Activations Density 0.014%

    No Known Activations