© 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. 833
    Prev
    Next
    INDEX
    Explanations

    wrap

    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
     rigor
    -0.08
     الو
    -0.08
    ustry
    -0.08
    istical
    -0.08
     sé
    -0.07
    cdr
    -0.07
     Anak
    -0.07
    िगत
    -0.07
     HOM
    -0.07
    hai
    -0.07
    POSITIVE LOGITS
     vap
    0.09
     Aub
    0.08
     Hel
    0.07
     ав
    0.07
     Jug
    0.07
     hel
    0.07
     Krist
    0.07
     Loft
    0.07
    bum
    0.07
     eman
    0.07
    Activations Density 0.008%

    No Known Activations