© 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. 11-RESID-POST-AA
    11. 543
    Prev
    Next
    INDEX
    Explanations

    Chinese electrical power systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IData
    -0.08
     Emilia
    -0.08
     Regel
    -0.08
     interchangeable
    -0.08
    θη
    -0.08
     Inline
    -0.07
    boxing
    -0.07
     Ramp
    -0.07
    Reusable
    -0.07
     THEY
    -0.07
    POSITIVE LOGITS
     solver
    0.08
     przedsiębior
    0.08
     pokoj
    0.08
     prese
    0.08
     donor
    0.08
     donors
    0.08
     adviser
    0.08
     rms
    0.07
     Rent
    0.07
     equilibrium
    0.07
    Activations Density 0.004%

    No Known Activations