© 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. 682
    Prev
    Next
    INDEX
    Explanations

    x

    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
    Kids
    -0.09
     Kids
    -0.09
     enfants
    -0.08
    �
    -0.08
    ೃದ್ಧ
    -0.08
    Questo
    -0.08
     Moines
    -0.08
     Bike
    -0.07
     samen
    -0.07
    ದಿಂದ
    -0.07
    POSITIVE LOGITS
     anot
    0.08
     Moor
    0.07
     在
    0.07
     graphite
    0.07
    @test
    0.07
     teg
    0.07
     ответы
    0.07
     integer
    0.07
     Thursday
    0.07
     CREATED
    0.07
    Activations Density 0.080%

    No Known Activations