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. 30777
    Prev
    Next
    INDEX
    Explanations

    arrangements and distributions

    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
    wein
    -0.08
     strerror
    -0.08
    adhi
    -0.08
     vergonha
    -0.08
    >alert
    -0.08
    -INF
    -0.07
    _fig
    -0.07
     Volks
    -0.07
    ukuru
    -0.07
     HUD
    -0.07
    POSITIVE LOGITS
     répart
    0.10
     balancing
    0.09
    Across
    0.09
    次数
    0.09
     распредел
    0.09
     distribution
    0.08
     Across
    0.08
    balanced
    0.08
     அதிக
    0.08
     abwechslungs
    0.08
    Activations Density 0.021%

    No Known Activations