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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31419
    Prev
    Next
    INDEX
    Explanations

    Thought

    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
    又爽
    -0.08
    ొన్నారు
    -0.08
     climax
    -0.08
     suffers
    -0.08
     ущер
    -0.08
    ొ
    -0.08
    主体
    -0.07
    -0.07
     محطم
    -0.07
     miserable
    -0.07
    POSITIVE LOGITS
     TCP
    0.08
     chaleure
    0.07
     आपको
    0.07
     refor
    0.07
    reth
    0.07
     libero
    0.07
     помнить
    0.07
     Think
    0.07
     gate
    0.07
     passionately
    0.07
    Activations Density 0.004%
    No Known Activations