© 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. 23-RESID-POST-AA
    11. 5430
    Prev
    Next
    INDEX
    Explanations

    linear

    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
     wickets
    -0.08
    වේ
    -0.08
     рах
    -0.07
     댓글
    -0.07
    Subscriber
    -0.07
     weddings
    -0.07
    ateurs
    -0.07
     tæ
    -0.07
    .Subscribe
    -0.07
     permalink
    -0.07
    POSITIVE LOGITS
     LP
    0.25
     optimization
    0.22
    LP
    0.21
     Optimization
    0.20
    optimization
    0.19
    Optimization
    0.19
     feasibility
    0.19
     programación
    0.18
     programming
    0.18
    _lp
    0.18
    Activations Density 0.034%

    No Known Activations