© 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. 78138
    Prev
    Next
    INDEX
    Explanations

    round

    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
    ctomy
    -0.09
     które
    -0.08
     destabil
    -0.08
     synonyms
    -0.08
     gefähr
    -0.08
    conce
    -0.08
     densely
    -0.08
     teadm
    -0.08
     spes
    -0.07
     Satan
    -0.07
    POSITIVE LOGITS
     faire
    0.09
     fairness
    0.09
     fashion
    0.08
     FIFO
    0.08
     очеред
    0.08
     Ф
    0.08
     ഫ
    0.08
     ফ
    0.08
     toegepast
    0.08
     fifo
    0.08
    Activations Density 0.003%

    No Known Activations