© 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. 12899
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     extent
    -0.08
     estr
    -0.08
     MS
    -0.08
     наз
    -0.08
     extens
    -0.08
     scrambling
    -0.08
     frig
    -0.08
     jerk
    -0.07
     ext
    -0.07
     sph
    -0.07
    POSITIVE LOGITS
    发行
    0.08
    Pars
    0.08
    美元
    0.08
    قبال
    0.08
     Stanley
    0.08
     entrance
    0.08
     dielectric
    0.08
    ∞
    0.07
    0.07
    CRT
    0.07
    Activations Density 0.045%
    No Known Activations