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. 44219
    Prev
    Next
    INDEX
    Explanations

    imaginary unit

    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
    記事
    -0.09
     eco
    -0.08
     flexibility
    -0.08
     parole
    -0.08
     graduating
    -0.08
     canopy
    -0.08
    gradu
    -0.08
     studying
    -0.08
     monopol
    -0.07
     эколог
    -0.07
    POSITIVE LOGITS
    ubi
    0.09
    acio
    0.08
    uga
    0.08
    uta
    0.08
    nią
    0.08
    urrence
    0.07
     distint
    0.07
    akit
    0.07
    uby
    0.07
    cial
    0.07
    Activations Density 0.017%

    No Known Activations