Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87874
    Prev
    Next
    INDEX
    Explanations

    classified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    men
    -0.08
    packed
    -0.07
     stakeholders
    -0.07
    kar
    -0.07
     seguida
    -0.07
     acog
    -0.07
    orra
    -0.07
    頻
    -0.07
     men
    -0.07
    pere
    -0.07
    POSITIVE LOGITS
     FAIL
    0.08
    923
    0.08
     Chancen
    0.08
     wrongful
    0.08
     Maschinen
    0.08
     Rubin
    0.07
     Zus
    0.07
    �
    0.07
    _queryset
    0.07
    859
    0.07
    Activations Density 0.000%

    No Known Activations