© 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. 99236
    Prev
    Next
    INDEX
    Explanations

    arm

    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
     ड
    -0.08
     banker
    -0.08
     Lik
    -0.07
     redd
    -0.07
     Negative
    -0.07
     കൊണ്ട
    -0.07
     egna
    -0.07
     మీద
    -0.07
     Petr
    -0.07
    Ä
    -0.07
    POSITIVE LOGITS
     của
    0.13
    ของ
    0.11
    าของ
    0.11
     της
    0.09
     ของ
    0.09
     сайта
    0.08
     των
    0.08
     Deutschlands
    0.08
     unseres
    0.08
    ك
    0.08
    Activations Density 0.537%

    No Known Activations