© 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. 26370
    Prev
    Next
    INDEX
    Explanations

    .

    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
     King's
    -0.09
    ，所以
    -0.08
    ολ
    -0.08
     соответственно
    -0.08
    ియు
    -0.08
     pér
    -0.08
    ，但是
    -0.08
    Kings
    -0.08
     নেত
    -0.08
     ales
    -0.07
    POSITIVE LOGITS
     SOP
    0.08
    ativa
    0.08
     Console
    0.08
     Gle
    0.08
    빛
    0.08
     Worte
    0.07
     Sofia
    0.07
     ner
    0.07
     Tv
    0.07
    ığım
    0.07
    Activations Density 0.040%

    No Known Activations