© 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. 496
    Prev
    Next
    INDEX
    Explanations

    cemic

    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
     Gor
    -0.09
     antar
    -0.08
     tril
    -0.08
    Tel
    -0.08
     existência
    -0.08
    Então
    -0.07
    Após
    -0.07
     sheriff
    -0.07
    ร้อง
    -0.07
    _PROCESS
    -0.07
    POSITIVE LOGITS
     веществ
    0.08
     sustancias
    0.08
     పద
    0.08
    affeine
    0.08
    _ratio
    0.08
     altre
    0.08
     cią
    0.08
     foods
    0.08
     potatoes
    0.07
     воздействия
    0.07
    Activations Density 0.003%

    No Known Activations