© 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. 45647
    Prev
    Next
    INDEX
    Explanations

    endian

    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
     derail
    -0.09
     precum
    -0.09
     halluc
    -0.08
     草
    -0.08
     cans
    -0.08
     כמו
    -0.08
     �
    -0.08
     体育
    -0.08
    368
    -0.08
    热线
    -0.08
    POSITIVE LOGITS
     endian
    0.15
    Endian
    0.14
    _ENDIAN
    0.11
    	byte
    0.09
    .Uint
    0.08
    	memcpy
    0.08
    顺
    0.08
    _BYTE
    0.08
     ordering
    0.08
     byte
    0.08
    Activations Density 0.002%

    No Known Activations