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. 105998
    Prev
    Next
    INDEX
    Explanations

    sight

    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
     outpatient
    -0.08
     unborn
    -0.08
     отнош
    -0.07
     অন্যতম
    -0.07
    ্র
    -0.07
    -own
    -0.07
    -acre
    -0.07
    べ
    -0.07
    relationships
    -0.07
     היח
    -0.07
    POSITIVE LOGITS
     altogether
    0.08
     commenting
    0.08
     immobil
    0.08
     vah
    0.08
     పో
    0.08
     Ecke
    0.08
     grazing
    0.07
     entirely
    0.07
     स्क्रीन
    0.07
     completamente
    0.07
    Activations Density 0.004%

    No Known Activations