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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95939
    Prev
    Next
    INDEX
    Explanations

    instrument

    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
     الدم
    -0.08
     infectious
    -0.08
    imulator
    -0.08
    ّه
    -0.08
    idays
    -0.07
    arf
    -0.07
    erl
    -0.07
    ieves
    -0.07
    +t
    -0.07
    +D
    -0.07
    POSITIVE LOGITS
     altogether
    0.08
     NAM
    0.07
     "./
    0.07
     सुन
    0.07
    ್ಬ
    0.07
     Spending
    0.07
     anbieten
    0.07
    .naming
    0.07
    ya
    0.07
    .Assert
    0.07
    Activations Density 0.000%

    No Known Activations