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. 53630
    Prev
    Next
    INDEX
    Explanations

    emotions

    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
     nagu
    -0.09
     dosis
    -0.08
     endeavor
    -0.07
     அனைவர
    -0.07
     рекоменду
    -0.07
     bear
    -0.07
    seks
    -0.07
     enthusiasts
    -0.07
    reifen
    -0.07
     году
    -0.07
    POSITIVE LOGITS
     outlook
    0.08
     appreciation
    0.08
     anticipation
    0.08
    (Not
    0.08
    /In
    0.08
     disbelief
    0.07
    \Carbon
    0.07
     Appreciation
    0.07
    stemming
    0.07
     чувство
    0.07
    Activations Density 0.034%

    No Known Activations