© 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. 31388
    Prev
    Next
    INDEX
    Explanations

    geo

    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
     اليد
    -0.08
     આંખ
    -0.07
     પૂર
    -0.07
     member
    -0.07
     бог
    -0.07
     hydraulic
    -0.07
     яй
    -0.07
     cholesterol
    -0.07
     હાથ
    -0.07
    اة
    -0.07
    POSITIVE LOGITS
    ഞ്ഞ
    0.09
     journalism
    0.09
    ത്സ
    0.09
     आधारित
    0.09
    ximity
    0.09
     गर्�
    0.08
    _hooks
    0.08
    fun
    0.08
     tailoring
    0.08
    Cuts
    0.08
    Activations Density 0.008%

    No Known Activations