© 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. 2662
    Prev
    Next
    INDEX
    Explanations

    ran

    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
    闪
    -0.09
     spontane
    -0.08
    博
    -0.08
    (parsed
    -0.08
     impartial
    -0.07
     England
    -0.07
     retard
    -0.07
    <<<<<<<<
    -0.07
     Mario
    -0.07
    pok
    -0.07
    POSITIVE LOGITS
     помогут
    0.08
     прит
    0.08
     zahtev
    0.07
     pomaga
    0.07
    احث
    0.07
    বিশ
    0.07
     Payments
    0.07
     tool
    0.07
    ייש
    0.07
     corrosion
    0.07
    Activations Density 0.000%

    No Known Activations