© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6314
    Prev
    Next
    INDEX
    Explanations

    Res

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chopped
    -0.10
     Novembre
    -0.09
    _language
    -0.09
     музыку
    -0.08
    .language
    -0.08
    青草
    -0.08
     Motivation
    -0.08
     motivation
    -0.08
     обучение
    -0.08
    language
    -0.08
    POSITIVE LOGITS
    Net
    0.17
     Net
    0.13
     net
    0.13
    net
    0.12
    _net
    0.12
     UN
    0.11
    -Net
    0.11
     NET
    0.11
    -net
    0.11
    UN
    0.10
    Activations Density 0.002%

    No Known Activations