© 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. 68091
    Prev
    Next
    INDEX
    Explanations

    level up

    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
     Helen
    -0.09
    ornado
    -0.07
     Daher
    -0.07
    ਪੀ
    -0.07
    ોપ
    -0.07
     पी
    -0.07
     Palmer
    -0.07
    [Double
    -0.07
     tpl
    -0.07
    ושט
    -0.07
    POSITIVE LOGITS
    izard
    0.08
     русский
    0.08
    'ing
    0.08
     encuentro
    0.08
     Россия
    0.07
     되는
    0.07
     россий
    0.07
    截图
    0.07
     generalized
    0.07
     Россий
    0.07
    Activations Density 0.005%

    No Known Activations