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. 77484
    Prev
    Next
    INDEX
    Explanations

    create

    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
    映画
    -0.08
    法律
    -0.08
     משפט
    -0.08
     Christmas
    -0.08
     obstruct
    -0.08
     voyeur
    -0.08
     offset
    -0.08
     vandal
    -0.08
     apprécier
    -0.08
     plaintiff
    -0.08
    POSITIVE LOGITS
     cantera
    0.09
     brew
    0.09
     probs
    0.09
     inplace
    0.09
     ein
    0.08
     caffe
    0.08
     Cognitive
    0.08
     Oromo
    0.08
     cognitive
    0.08
     ubuntu
    0.08
    Activations Density 0.003%

    No Known Activations