© 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. 30849
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
     п
    -0.08
     Capital
    -0.08
    围
    -0.08
    -0.08
    -0.08
    �
    -0.07
    Capital
    -0.07
    ച
    -0.07
     dramatic
    -0.07
     Overall
    -0.07
    POSITIVE LOGITS
     sani
    0.10
     Sekunden
    0.10
     timmar
    0.10
    Seconds
    0.09
    _seconds
    0.09
     timers
    0.09
    _velocity
    0.09
     секун
    0.09
    _vel
    0.09
     секунд
    0.09
    Activations Density 0.048%
    No Known Activations