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. 129743
    Prev
    Next
    INDEX
    Explanations

    gerrymandering

    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
    MOD
    -0.08
     useful
    -0.08
     tut
    -0.07
    direct
    -0.07
     bottom
    -0.07
     Helm
    -0.07
    bottom
    -0.07
     Sik
    -0.07
    kd
    -0.07
    atrib
    -0.07
    POSITIVE LOGITS
     unconstitutional
    0.11
     unequal
    0.10
     unfair
    0.09
     redistribution
    0.09
     Redistributions
    0.09
     zoning
    0.09
     inequ
    0.09
    (instance
    0.09
    公平
    0.09
    ировку
    0.09
    Activations Density 0.012%

    No Known Activations