© 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. 2775
    Prev
    Next
    INDEX
    Explanations

    gyz

    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
    Head
    -0.09
    穿
    -0.08
     Head
    -0.08
     definite
    -0.08
     peptide
    -0.08
    urdue
    -0.08
     clips
    -0.08
     transf
    -0.07
     adev
    -0.07
    demo
    -0.07
    POSITIVE LOGITS
     bankruptcy
    0.08
     നിയന്ത്ര
    0.08
    权益
    0.07
    Resp
    0.07
     gambling
    0.07
    _resp
    0.07
    _utf
    0.07
     дър
    0.07
     Darm
    0.07
     appla
    0.07
    Activations Density 0.000%

    No Known Activations