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. 103378
    Prev
    Next
    INDEX
    Explanations

    acid

    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
     ambitious
    -0.08
    velop
    -0.07
    าห
    -0.07
     Freel
    -0.07
     ambitie
    -0.07
    efa
    -0.07
     strutt
    -0.07
    Empire
    -0.07
     Mob
    -0.07
     mama
    -0.07
    POSITIVE LOGITS
    ;padding
    0.09
     ไ
    0.09
    ;color
    0.08
     দ্র
    0.08
     dissolved
    0.08
     الكيمي
    0.08
    ittest
    0.08
    isión
    0.08
     سید
    0.08
    -loaded
    0.08
    Activations Density 0.001%

    No Known Activations