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. 61036
    Prev
    Next
    INDEX
    Explanations

    centric

    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
    507
    -0.08
     Merr
    -0.08
    zend
    -0.08
     ach
    -0.08
     samp
    -0.07
    ulet
    -0.07
     President
    -0.07
     bal
    -0.07
     anal
    -0.07
    dap
    -0.07
    POSITIVE LOGITS
     enterprises
    0.08
    ály
    0.07
    =center
    0.07
    มน
    0.07
     affair
    0.07
    kun
    0.07
    (Int
    0.07
     wholesale
    0.07
     establishments
    0.06
     نارو
    0.06
    Activations Density 0.005%

    No Known Activations