© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 973
    Prev
    Next
    INDEX
    Explanations

    made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     convictions
    -0.09
     اسلام
    -0.07
     panan
    -0.07
     pamam
    -0.07
     porch
    -0.07
     sodium
    -0.07
     refor
    -0.07
     entirely
    -0.07
    嫁
    -0.07
     weakness
    -0.07
    POSITIVE LOGITS
     MID
    0.08
     During
    0.08
    HAS
    0.08
    chalk
    0.08
     CRE
    0.08
    ’int
    0.08
    ometry
    0.07
    During
    0.07
    eep
    0.07
     Peng
    0.07
    Activations Density 0.000%

    No Known Activations