© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45228
    Prev
    Next
    INDEX
    Explanations

    chess openings/strategy

    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
     nonprofit
    -0.11
     emboss
    -0.11
     nonprofits
    -0.10
     정부
    -0.10
     UNESCO
    -0.10
     цифров
    -0.09
     embossed
    -0.09
     அரசு
    -0.09
     пластиков
    -0.09
     инвалид
    -0.09
    POSITIVE LOGITS
     tactical
    0.12
     opponent
    0.11
     tactics
    0.11
     bankroll
    0.11
     Tactical
    0.10
    残局
    0.10
     attacking
    0.10
    Opponent
    0.10
    Winning
    0.10
     ആക്രമ
    0.10
    Activations Density 0.016%

    No Known Activations