© 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. 15-RESID-POST-AA
    11. 16591
    Prev
    Next
    INDEX
    Explanations

    Wine descriptions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crowdfunding
    -0.08
     textbooks
    -0.08
     collisions
    -0.08
     sabotage
    -0.07
     logist
    -0.07
     оборудования
    -0.07
     humains
    -0.07
     télécharg
    -0.07
    -0.07
     иди
    -0.07
    POSITIVE LOGITS
     creamy
    0.12
     airy
    0.10
     moderate
    0.10
     aromas
    0.10
     brid
    0.09
     mellow
    0.09
     느낌
    0.09
     wirkt
    0.09
     fruity
    0.09
     mild
    0.09
    Activations Density 0.043%
    No Known Activations