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. 78769
    Prev
    Next
    INDEX
    Explanations

    retrying

    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
     Argent
    -0.09
     deed
    -0.08
     ratios
    -0.08
     bald
    -0.08
     wow
    -0.08
    lide
    -0.07
     Shiv
    -0.07
    .tool
    -0.07
    favicon
    -0.07
     Everywhere
    -0.07
    POSITIVE LOGITS
     независ
    0.09
    _SECOND
    0.09
     unabhängig
    0.09
     subsequent
    0.09
    -after
    0.09
     полноцен
    0.08
     unconditional
    0.08
     независимо
    0.08
     незалеж
    0.08
     onafh
    0.08
    Activations Density 0.011%

    No Known Activations