© 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. 3-RESID-POST-AA
    11. 13152
    Prev
    Next
    INDEX
    Explanations

    LAB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DMA
    -0.08
    티
    -0.07
     boon
    -0.07
     nešto
    -0.07
    ərə
    -0.07
     حالة
    -0.07
     corrobor
    -0.07
     temi
    -0.06
     thanks
    -0.06
     proporciona
    -0.06
    POSITIVE LOGITS
    گاه
    0.09
    Lets
    0.08
    975
    0.08
    _SUP
    0.08
    -ons
    0.08
    xes
    0.08
    396
    0.08
    497
    0.07
     happenings
    0.07
    olated
    0.07
    Activations Density 0.002%

    No Known Activations