© 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. 23-RESID-POST-AA
    11. 97371
    Prev
    Next
    INDEX
    Explanations

    уб

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouverte
    -0.08
    metry
    -0.08
    etric
    -0.08
    ń
    -0.08
    illisecond
    -0.07
     fundamental
    -0.07
    េង
    -0.07
     secured
    -0.07
    эп
    -0.07
    enspiel
    -0.07
    POSITIVE LOGITS
    ира
    0.16
    расы
    0.15
    рала
    0.12
    ивает
    0.12
    іра
    0.11
    ерите
    0.10
    ер
    0.10
    рали
    0.10
    рал
    0.10
    ь
    0.10
    Activations Density 0.002%

    No Known Activations