© 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. 3-RESID-POST-AA
    11. 13160
    Prev
    Next
    INDEX
    Explanations

    pricing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coch
    -0.08
     constr
    -0.07
     mejora
    -0.07
    mente
    -0.07
     объ
    -0.07
     Resist
    -0.07
     sell
    -0.07
    WW
    -0.07
     weaknesses
    -0.07
     unscr
    -0.07
    POSITIVE LOGITS
    IOS
    0.08
     lans
    0.08
     bear
    0.08
     Cli
    0.08
     Eld
    0.07
     Laws
    0.07
    unjung
    0.07
    trad
    0.07
     Joshua
    0.07
    Cli
    0.07
    Activations Density 0.010%

    No Known Activations