Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91176
    Prev
    Next
    INDEX
    Explanations

    Taxes and claiming dependents

    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
    兑
    -0.08
    logos
    -0.08
     Fade
    -0.08
    ahlukene
    -0.08
     darüber
    -0.08
     Logos
    -0.08
     खोल
    -0.08
     kontinuier
    -0.08
     comerciais
    -0.08
    .what
    -0.08
    POSITIVE LOGITS
    父
    0.11
     caregiver
    0.10
     parents
    0.09
     relatives
    0.08
     careg
    0.08
    共享
    0.08
     esperanza
    0.08
    ibling
    0.08
     eldest
    0.08
    爸爸
    0.08
    Activations Density 0.009%

    No Known Activations