© 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. 19-RESID-POST-AA
    11. 103451
    Prev
    Next
    INDEX
    Explanations

    only

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kandi
    -0.11
     plutôt
    -0.10
     molto
    -0.09
     erittäin
    -0.09
     kakhulu
    -0.09
     Very
    -0.09
     paljon
    -0.09
    ，非常
    -0.09
     vrlo
    -0.09
     pochi
    -0.09
    POSITIVE LOGITS
     as
    0.10
     understandable
    0.08
     meaningful
    0.08
     tohoto
    0.08
    üml
    0.08
    Successful
    0.08
     appreciated
    0.08
    _possible
    0.08
    _available
    0.08
     successful
    0.08
    Activations Density 0.005%

    No Known Activations