© 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. 44351
    Prev
    Next
    INDEX
    Explanations

    750

    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
     User
    -0.09
     Normally
    -0.08
     Tabelle
    -0.08
     Versorgung
    -0.08
     Originally
    -0.07
     chemically
    -0.07
     характ
    -0.07
    所谓
    -0.07
     Déf
    -0.07
     Telephone
    -0.07
    POSITIVE LOGITS
    াশ
    0.08
     clim
    0.08
     cringe
    0.08
     diligence
    0.07
    泊
    0.07
     peregr
    0.07
    /year
    0.07
    하거나
    0.07
    暖
    0.07
     cog
    0.07
    Activations Density 0.003%

    No Known Activations