© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24758
    Prev
    Next
    INDEX
    Explanations

    metacognition

    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
     civilization
    -0.09
     Rhode
    -0.08
     Rés
    -0.08
     já
    -0.08
     Nylon
    -0.08
    ้าง
    -0.08
    ിട
    -0.08
    난
    -0.08
     locale
    -0.08
     immort
    -0.07
    POSITIVE LOGITS
     शिक्ष
    0.08
     Dont
    0.08
    ognitive
    0.08
     cogn
    0.08
    _ARM
    0.07
     fortale
    0.07
     voluntary
    0.07
     treg
    0.07
     inici
    0.07
     sut
    0.07
    Activations Density 0.002%

    No Known Activations