© 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. 15-RESID-POST-AA
    11. 16645
    Prev
    Next
    INDEX
    Explanations

    polka dots

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Complex
    -0.08
     komplex
    -0.08
     विधानसभा
    -0.08
    ipelago
    -0.08
    остоя
    -0.08
     Conservation
    -0.08
    aleo
    -0.08
     соревн
    -0.08
     растений
    -0.08
    sette
    -0.07
    POSITIVE LOGITS
     cough
    0.09
     bubble
    0.09
    0.09
     laughter
    0.09
     laughs
    0.08
     laugh
    0.08
     encanto
    0.08
     charm
    0.08
     bubbles
    0.08
     universe
    0.08
    Activations Density 0.002%
    No Known Activations