© 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. 31153
    Prev
    Next
    INDEX
    Explanations

    Physics and math problems

    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
    097
    -0.08
    infect
    -0.08
     enjoyable
    -0.08
    archives
    -0.08
     pât
    -0.08
    seed
    -0.08
     censor
    -0.08
     mould
    -0.08
    írus
    -0.08
     ambit
    -0.08
    POSITIVE LOGITS
     torque
    0.14
    Torque
    0.14
     Torque
    0.13
     forças
    0.11
     fuerzas
    0.11
     magnitude
    0.10
     Force
    0.10
     Electric
    0.10
     opposing
    0.10
     Kräfte
    0.10
    Activations Density 0.018%

    No Known Activations