© 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. 54365
    Prev
    Next
    INDEX
    Explanations

    ails

    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
     complemented
    -0.08
    湘
    -0.08
     embodiment
    -0.07
     exempl
    -0.07
    orst
    -0.07
     finished
    -0.07
     hosts
    -0.07
     scanned
    -0.07
     অতিথ
    -0.07
    Grade
    -0.07
    POSITIVE LOGITS
     TER
    0.08
     ആരാധ
    0.08
     doe
    0.08
     соз
    0.08
     Kremlin
    0.08
    TAIL
    0.07
     rinn
    0.07
     стало
    0.07
     Around
    0.07
     Tes
    0.07
    Activations Density 0.001%

    No Known Activations