© 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. 29391
    Prev
    Next
    INDEX
    Explanations

    integer

    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
     afectados
    -0.08
    mong
    -0.08
     후보
    -0.08
     coth
    -0.07
     inflamm
    -0.07
     comeback
    -0.07
    afone
    -0.07
     expelled
    -0.07
     Candidate
    -0.07
     Ernesto
    -0.07
    POSITIVE LOGITS
    -minute
    0.08
     wavelengths
    0.08
     doses
    0.08
     minutes
    0.08
    -linear
    0.08
     coordinates
    0.08
     headlights
    0.07
     நகர
    0.07
     seats
    0.07
    -scal
    0.07
    Activations Density 0.016%

    No Known Activations