© 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. 45439
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
    äter
    -0.08
     поможет
    -0.08
    -0.08
    전을
    -0.08
    _mem
    -0.08
    वार
    -0.07
    .lab
    -0.07
    एफ
    -0.07
    전에
    -0.07
    veel
    -0.07
    POSITIVE LOGITS
     Rial
    0.09
     Actually
    0.09
     yes
    0.08
    Yes
    0.08
     Ostr
    0.08
     Essence
    0.08
     eso
    0.08
     orchid
    0.08
     Montenegro
    0.08
    Actually
    0.08
    Activations Density 0.245%
    No Known Activations