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. 46716
    Prev
    Next
    INDEX
    Explanations

    Professions

    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
     связано
    -0.08
    دىكى
    -0.08
     Presidency
    -0.08
    عود
    -0.08
     comun
    -0.07
     imperial
    -0.07
    లో
    -0.07
     parental
    -0.07
     holog
    -0.07
    noun
    -0.07
    POSITIVE LOGITS
    *innen
    0.18
    :innen
    0.17
    innen
    0.15
    들에게
    0.15
    们
    0.15
    에게
    0.14
    Innen
    0.12
    들이
    0.12
    들의
    0.12
     ஒருவர்
    0.12
    Activations Density 0.791%

    No Known Activations