© 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. 47542
    Prev
    Next
    INDEX
    Explanations

    =

    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
     সিদ্ধান্ত
    -0.08
     whakata
    -0.08
     বাস
    -0.08
     restrictions
    -0.07
     দায়
    -0.07
     û
    -0.07
     usual
    -0.07
     Retour
    -0.07
     আমরা
    -0.07
     engine
    -0.07
    POSITIVE LOGITS
     divisible
    0.08
    Salvar
    0.08
    Sleep
    0.08
     ряда
    0.08
     thirty
    0.08
    番号
    0.08
    ે
    0.08
     unes
    0.07
     arco
    0.07
    콘
    0.07
    Activations Density 0.006%

    No Known Activations