© 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. 23-RESID-POST-AA
    6. 97772
    Prev
    Next
    INDEX
    Explanations

    Pr

    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
    িল
    -0.08
     ouvert
    -0.08
     SIL
    -0.08
    ಿಲ
    -0.07
     Silk
    -0.07
     durchgeführt
    -0.07
     auff
    -0.07
     unreal
    -0.07
     phase
    -0.07
     textbook
    -0.07
    POSITIVE LOGITS
    ática
    0.15
    áticas
    0.14
    ático
    0.13
    áticos
    0.13
    atic
    0.13
    ÁT
    0.12
    áticamente
    0.11
    ótese
    0.11
    ensagem
    0.11
    atique
    0.10
    Activations Density 0.000%

    No Known Activations