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. 27494
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Unicode
    -0.08
     �
    -0.08
     hairstyle
    -0.07
    urface
    -0.07
     computer
    -0.07
    estad
    -0.07
    kih
    -0.07
    -language
    -0.07
    Unicode
    -0.07
     yourself
    -0.07
    POSITIVE LOGITS
    杭州
    0.10
    浙江
    0.09
     basta
    0.09
    安徽
    0.09
     江苏
    0.09
    ifes
    0.08
    ANTES
    0.08
    990
    0.08
     就
    0.08
    Months
    0.08
    Activations Density 0.542%

    No Known Activations