© 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. 3093
    Prev
    Next
    INDEX
    Explanations

    own

    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
     accolades
    -0.10
     MIR
    -0.08
     sunflower
    -0.07
    Winner
    -0.07
     advoc
    -0.07
    iquement
    -0.07
     culinary
    -0.07
     মাত্র
    -0.07
    uket
    -0.07
     круг
    -0.07
    POSITIVE LOGITS
     ramp
    0.10
    Ramp
    0.09
     Ramp
    0.08
     phr
    0.08
    Ark
    0.08
    δ
    0.08
     soc
    0.07
    sr
    0.07
     poz
    0.07
     Angriff
    0.07
    Activations Density 0.009%

    No Known Activations