© 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. 23-RESID-POST-AA
    11. 49829
    Prev
    Next
    INDEX
    Explanations

    .com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satellites
    -0.11
     satellite
    -0.10
     Satell
    -0.09
    Satellite
    -0.09
     Satellite
    -0.09
     repository
    -0.09
     basi
    -0.09
    ต่ํา
    -0.08
     Wikipedia
    -0.08
     DOWN
    -0.08
    POSITIVE LOGITS
     Incl
    0.09
     böl
    0.09
     incl
    0.09
    material
    0.08
     material
    0.08
    ,const
    0.08
    mega
    0.08
     탐
    0.08
     rápidamente
    0.08
     материал
    0.08
    Activations Density 0.001%

    No Known Activations