© 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. 64653
    Prev
    Next
    INDEX
    Explanations

    Exponents in math problems

    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
    facet
    -0.09
    *p
    -0.08
     debris
    -0.08
    �
    -0.08
    -hole
    -0.07
    dej
    -0.07
     Editorial
    -0.07
     пара
    -0.07
    phes
    -0.07
    asured
    -0.07
    POSITIVE LOGITS
     thr
    0.08
     Powers
    0.08
     powers
    0.08
     lang
    0.07
     transforms
    0.07
     vín
    0.07
     teal
    0.07
    翁
    0.07
     sekali
    0.07
     intre
    0.07
    Activations Density 0.025%

    No Known Activations