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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26005
    Prev
    Next
    INDEX
    Explanations

    natural

    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
    irio
    -0.08
     ਸਾਹ
    -0.08
    ’ব
    -0.08
     первом
    -0.07
     Nicht
    -0.07
     besteh
    -0.07
     masih
    -0.07
    ’as
    -0.07
     అనే
    -0.07
     ಅಧ
    -0.07
    POSITIVE LOGITS
     naturally
    0.13
    天然
    0.12
     naturellement
    0.12
     natural
    0.11
     inherently
    0.11
     naturalmente
    0.11
     inherent
    0.11
    sprekend
    0.10
    自然
    0.10
     naturel
    0.10
    Activations Density 0.033%

    No Known Activations