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. 119339
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
     malls
    -0.08
    融合
    -0.07
    街
    -0.07
    blend
    -0.07
     icon
    -0.07
    -0.07
    炎
    -0.07
    andas
    -0.07
    .union
    -0.07
    Bloom
    -0.07
    POSITIVE LOGITS
     जीत
    0.12
     જીત
    0.12
    残局
    0.11
     Countdown
    0.11
     खेल
    0.11
     opponent
    0.10
    Opponent
    0.10
     विपक्ष
    0.10
    Countdown
    0.10
     ходе
    0.10
    Activations Density 0.021%

    No Known Activations