© 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. 15-RESID-POST-AA
    6. 16271
    Prev
    Next
    INDEX
    Explanations

    |

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cj
    -0.07
     don't
    -0.07
     configure
    -0.07
     exceptionally
    -0.07
    issue
    -0.07
    s
    -0.07
     extraordinarily
    -0.07
    configure
    -0.07
     issue
    -0.07
    BK
    -0.07
    POSITIVE LOGITS
    ستخدمة
    0.11
     Обычно
    0.11
     часто
    0.10
    -example
    0.10
     voorbeelden
    0.10
     غالب
    0.10
    Often
    0.10
    通常
    0.10
     Often
    0.10
    ередко
    0.10
    Activations Density 0.011%

    No Known Activations