© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1282
    Prev
    Next
    INDEX
    Explanations

    Screen displays

    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
    409
    -0.07
     sahibi
    -0.07
     riv
    -0.07
    -0.07
    978
    -0.07
     domin
    -0.07
     capita
    -0.07
     gobern
    -0.07
     caval
    -0.07
     ett
    -0.07
    POSITIVE LOGITS
    گاهی
    0.09
    бат
    0.08
     Bale
    0.08
     Zou
    0.08
     pli
    0.08
    Ei
    0.08
     assust
    0.08
     Beyoncé
    0.08
     stet
    0.07
     prøve
    0.07
    Activations Density 0.015%
    No Known Activations