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

    Neuronpedia

    Jacobian LensNEW
    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. 63621
    Prev
    Next
    INDEX
    Explanations

    example/instance

    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
     优
    -0.07
     interessiert
    -0.07
    मेल
    -0.07
    Optimize
    -0.07
     نهاية
    -0.07
     optimizing
    -0.07
    apor
    -0.07
    'ins
    -0.07
    _opt
    -0.07
     carriers
    -0.07
    POSITIVE LOGITS
     exempl
    0.12
    Example
    0.11
    example
    0.11
     ejemplo
    0.11
     exemplo
    0.11
     evident
    0.11
     evidenced
    0.10
    _example
    0.10
     esempio
    0.10
     famously
    0.10
    Activations Density 0.292%

    No Known Activations