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. 48944
    Prev
    Next
    INDEX
    Explanations

    Connection (mathematical, geometrical)

    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
     Memory
    -0.08
    Memory
    -0.08
    Oz
    -0.08
    ois
    -0.08
     kanye
    -0.08
    det
    -0.08
     এবং
    -0.08
    ụụ
    -0.07
     aposent
    -0.07
     환경
    -0.07
    POSITIVE LOGITS
     connecting
    0.13
     Connecting
    0.11
     линии
    0.11
    connecting
    0.11
     connections
    0.11
     ಸಂಪರ್ಕ
    0.11
     connects
    0.10
     лини
    0.10
    线路
    0.10
     मार्ग
    0.10
    Activations Density 0.090%

    No Known Activations