© 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. 23-RESID-POST-AA
    11. 6592
    Prev
    Next
    INDEX
    Explanations

    rel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ných
    -0.08
    translate
    -0.08
     rhetoric
    -0.08
     preko
    -0.08
     νέ
    -0.08
     fazem
    -0.08
     ireo
    -0.08
     courteous
    -0.08
     vocabulary
    -0.08
    nými
    -0.08
    POSITIVE LOGITS
    itag
    0.08
    ache
    0.08
    ACHE
    0.08
    Ii
    0.08
    Ie
    0.07
     שק
    0.07
    Iy
    0.07
    ie
    0.07
    惠
    0.07
    ani
    0.07
    Activations Density 0.000%

    No Known Activations