© 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. 48850
    Prev
    Next
    INDEX
    Explanations

    Tagalog

    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
     zhv
    -0.08
     пове
    -0.08
     زم
    -0.08
    ouz
    -0.08
     توسعه
    -0.08
     whakahaere
    -0.08
     dezvolt
    -0.08
    énagement
    -0.07
     organisation
    -0.07
     проц
    -0.07
    POSITIVE LOGITS
     dibdib
    0.15
     bulate
    0.14
     buhok
    0.13
     gabi
    0.13
     tiyan
    0.13
     tubig
    0.12
    -singaw
    0.12
     apoy
    0.12
     itlog
    0.12
     mawala
    0.12
    Activations Density 0.001%

    No Known Activations