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. 113959
    Prev
    Next
    INDEX
    Explanations

    location/estimation in physical space

    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
     champ
    -0.08
    agog
    -0.08
    ebilir
    -0.07
     Chr
    -0.07
    Forgot
    -0.07
     Pickup
    -0.07
     Dire
    -0.07
    ifiquement
    -0.07
    lief
    -0.07
     Champ
    -0.07
    POSITIVE LOGITS
     exceed
    0.09
     مستويات
    0.09
     уровня
    0.09
     thresholds
    0.09
    值
    0.08
     exceeds
    0.08
     adequ
    0.08
    راوح
    0.08
    ระดับ
    0.08
     eche
    0.08
    Activations Density 0.086%

    No Known Activations