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. 49486
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    估
    -0.08
    重新
    -0.07
    异常
    -0.07
    毫
    -0.07
    仍
    -0.07
    局
    -0.07
    -Le
    -0.07
     reboot
    -0.07
    当
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    mono
    0.08
     terrenos
    0.08
    hose
    0.08
     Remarks
    0.08
    Remarks
    0.08
    },↵↵
    0.08
     observational
    0.08
     വ്യാപ
    0.07
    commended
    0.07
     Comunidad
    0.07
    Activations Density 0.014%

    No Known Activations