Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9009
    Prev
    Next
    INDEX
    Explanations

    roles and responsibilities

    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
     Wynn
    -0.08
     surrogate
    -0.08
     Нью
    -0.08
     verdi
    -0.08
     vermelho
    -0.08
     банк
    -0.07
    trent
    -0.07
     seguito
    -0.07
    897
    -0.07
     trillion
    -0.07
    POSITIVE LOGITS
    側
    0.09
    則
    0.08
    (flags
    0.08
     maupun
    0.08
     fémin
    0.08
    则
    0.08
    ],
    0.08
     plugs
    0.08
     ವರ
    0.08
    erseits
    0.08
    Activations Density 0.092%

    No Known Activations