© 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. 95573
    Prev
    Next
    INDEX
    Explanations

    Tired or unwell 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
     Cathedral
    -0.08
     presyo
    -0.08
    things
    -0.08
     Lesser
    -0.08
     zahr
    -0.08
     Greater
    -0.08
    stations
    -0.07
     pona
    -0.07
     портал
    -0.07
     Міні
    -0.07
    POSITIVE LOGITS
     beein
    0.10
     bruis
    0.08
    а
    0.08
     warmed
    0.08
     interessieren
    0.07
     dust
    0.07
     painted
    0.07
     rồi
    0.07
    صبح
    0.07
     chứa
    0.07
    Activations Density 0.030%

    No Known Activations