© 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. 7-RESID-POST-AA
    11. 1143
    Prev
    Next
    INDEX
    Explanations

    dwarf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whirlpool
    -0.08
     traj
    -0.07
     porod
    -0.07
     salmon
    -0.07
     prescribing
    -0.07
     mercanc
    -0.07
     wired
    -0.07
     #[
    -0.07
     industrial
    -0.07
     vital
    -0.07
    POSITIVE LOGITS
    aign
    0.09
     ಹೆ
    0.09
    UIScreen
    0.09
     Mehrheit
    0.08
     Anna
    0.08
    Illuminate
    0.07
    Weak
    0.07
    Anna
    0.07
    creens
    0.07
     blitt
    0.07
    Activations Density 0.001%

    No Known Activations