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. 112674
    Prev
    Next
    INDEX
    Explanations

    Structures

    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
     begleiten
    -0.08
     उठ
    -0.08
     לא
    -0.08
     ಹು
    -0.08
     руковод
    -0.07
     vuur
    -0.07
     Attendance
    -0.07
    Inbound
    -0.07
     Lup
    -0.07
    -т
    -0.07
    POSITIVE LOGITS
     구조
    0.10
    .Struct
    0.10
    结构
    0.10
    .struct
    0.09
    .structure
    0.09
    構
    0.08
     રચ
    0.08
     strukt
    0.08
    -changing
    0.08
    மை
    0.08
    Activations Density 0.044%

    No Known Activations