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. 43074
    Prev
    Next
    INDEX
    Explanations

    empty

    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
     mor
    -0.08
     pu
    -0.08
     constit
    -0.08
    Mor
    -0.08
     Mor
    -0.08
    -0.08
    不上
    -0.07
     Ia
    -0.07
     Freder
    -0.07
    cp
    -0.07
    POSITIVE LOGITS
    -handed
    0.09
     Syl
    0.09
    闲
    0.09
    IRONMENT
    0.08
     Chamber
    0.08
    聊
    0.08
    -headed
    0.07
    掉
    0.07
    র্তি
    0.07
    jár
    0.07
    Activations Density 0.010%

    No Known Activations