© 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. 75839
    Prev
    Next
    INDEX
    Explanations

    quadratic equations

    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
    hes
    -0.08
    חו
    -0.07
    HR
    -0.07
    Appe
    -0.07
    chr
    -0.07
     accessible
    -0.07
     attentive
    -0.07
     emerg
    -0.07
    HC
    -0.07
     supportive
    -0.07
    POSITIVE LOGITS
     mst
    0.09
     connaît
    0.09
    യെ
    0.09
    <arr
    0.08
    界
    0.08
     આવે
    0.08
    위를
    0.08
    որը
    0.08
     કરતાં
    0.08
     Kutani
    0.08
    Activations Density 0.030%

    No Known Activations