© 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. 13195
    Prev
    Next
    INDEX
    Explanations

    INTO

    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
    anne
    -0.09
    ించి
    -0.08
    ocu
    -0.08
     entend
    -0.08
    departure
    -0.07
    ించ
    -0.07
    Segue
    -0.07
     bire
    -0.07
     ज्य
    -0.07
     quen
    -0.07
    POSITIVE LOGITS
     wildlife
    0.08
     Î
    0.07
     refugee
    0.07
     scatter
    0.07
     harp
    0.07
     Pedro
    0.07
     Wildlife
    0.07
     Gar
    0.07
     Proc
    0.07
     Qui
    0.07
    Activations Density 0.001%

    No Known Activations