© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30171
    Prev
    Next
    INDEX
    Explanations

    p, q, a

    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
     ピ
    -0.08
     ഈ
    -0.08
    agma
    -0.08
    بى
    -0.08
    OVID
    -0.08
     ഇത്ത
    -0.08
    amada
    -0.08
     indicação
    -0.08
    皇
    -0.07
     上午
    -0.07
    POSITIVE LOGITS
    ，但是
    0.07
    บท
    0.07
    ELS
    0.07
     hyvin
    0.07
     much
    0.07
     follows
    0.07
    ικά
    0.07
     manifold
    0.07
     implies
    0.07
    izr
    0.07
    Activations Density 0.009%

    No Known Activations