© 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. 25273
    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
     estaria
    -0.09
     estiver
    -0.08
     estão
    -0.08
     suplement
    -0.07
     ceg
    -0.07
     completely
    -0.07
     contas
    -0.07
     vêm
    -0.07
     شيء
    -0.07
     تح
    -0.07
    POSITIVE LOGITS
     aptly
    0.11
     bezeichnet
    0.10
     genoemd
    0.09
    简称
    0.09
     ethos
    0.08
     कहल
    0.08
    ฤษภาคม
    0.08
     કહેવ
    0.08
     എന്നാണ്
    0.08
     kuts
    0.08
    Activations Density 0.094%

    No Known Activations