© 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. 45694
    Prev
    Next
    INDEX
    Explanations

    face

    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
     PSL
    -0.08
     pokies
    -0.08
     empirical
    -0.07
    ប្រ�
    -0.07
     PS
    -0.07
    ක්
    -0.07
     Parliament
    -0.07
    (Index
    -0.07
    ypass
    -0.07
     Lisboa
    -0.07
    POSITIVE LOGITS
     serene
    0.09
     meticulously
    0.08
     gently
    0.08
     narrowly
    0.08
     emphasize
    0.08
    描
    0.08
     positioned
    0.08
     शांत
    0.08
     微
    0.08
    iska
    0.07
    Activations Density 0.009%

    No Known Activations