© 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. 30119
    Prev
    Next
    INDEX
    Explanations

    personality types

    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
     projectile
    -0.09
     limousine
    -0.08
     furnace
    -0.08
     almal
    -0.08
    缴
    -0.08
     vimos
    -0.08
     quaternion
    -0.08
     accumulator
    -0.08
     nuclé
    -0.08
    '})
    -0.08
    POSITIVE LOGITS
    Pers
    0.07
    Excel
    0.07
     Prag
    0.07
     Excel
    0.07
     വ്യക്ത
    0.07
    ować
    0.07
    ck
    0.07
    cı
    0.07
    冒
    0.07
     vent
    0.07
    Activations Density 0.033%

    No Known Activations