© 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. 11-RESID-POST-AA
    11. 29629
    Prev
    Next
    INDEX
    Explanations

    В

    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
    _dl
    -0.08
    /stretch
    -0.08
     చాల
    -0.08
     emphasis
    -0.08
     Ole
    -0.07
    $content
    -0.07
    $p
    -0.07
     emphasized
    -0.07
     Zir
    -0.07
     dicht
    -0.07
    POSITIVE LOGITS
    Dear
    0.09
    ברת
    0.08
    Please
    0.08
    СТ
    0.08
     день
    0.08
    АН
    0.08
     пог
    0.08
     please
    0.08
    Overview
    0.08
     пожалуйста
    0.07
    Activations Density 0.040%

    No Known Activations