© 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. 75675
    Prev
    Next
    INDEX
    Explanations

    V-model

    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
     flooring
    -0.07
     humid
    -0.07
     countless
    -0.07
     હુમ
    -0.07
     jurisdiction
    -0.07
     Quint
    -0.07
     gespeichert
    -0.07
    _PM
    -0.06
     తాజ
    -0.06
    ازی
    -0.06
    POSITIVE LOGITS
    olve
    0.09
     ROC
    0.09
     jednost
    0.08
    perfil
    0.08
     spett
    0.08
    Matching
    0.08
    framt
    0.08
    /ver
    0.08
     SPORT
    0.08
    bloc
    0.08
    Activations Density 0.001%

    No Known Activations