© 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. 7-RESID-POST-AA
    11. 1245
    Prev
    Next
    INDEX
    Explanations

    fatty acids

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gong
    -0.09
    И
    -0.08
     plaque
    -0.08
    스토
    -0.08
    �
    -0.08
    alaki
    -0.07
    irq
    -0.07
     tratando
    -0.07
     salt
    -0.07
    mas
    -0.07
    POSITIVE LOGITS
     vr
    0.08
     vid
    0.08
     Mek
    0.08
    Vid
    0.07
     க
    0.07
     Kara
    0.07
     सं
    0.07
     तर
    0.07
     Vid
    0.07
     Huss
    0.07
    Activations Density 0.002%

    No Known Activations