© 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. 64548
    Prev
    Next
    INDEX
    Explanations

    Punctuation and non-alphanumeric characters

    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
     Connecticut
    -0.09
    ervers
    -0.09
     degelijk
    -0.08
    評
    -0.08
    urances
    -0.08
     matlab
    -0.08
    yses
    -0.08
    eur
    -0.08
     plight
    -0.08
     assesses
    -0.08
    POSITIVE LOGITS
     híbr
    0.10
     hybrid
    0.10
     hybride
    0.10
    Hybrid
    0.09
     Hybrid
    0.09
     hybrids
    0.09
     ransomware
    0.09
     seamless
    0.08
     immersive
    0.08
    越来越
    0.08
    Activations Density 0.033%

    No Known Activations