© 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. 129321
    Prev
    Next
    INDEX
    Explanations

    The

    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
     suje
    -0.09
     aforementioned
    -0.09
    !!!!!
    -0.08
     plethora
    -0.08
    тер
    -0.08
     cuer
    -0.07
     rell
    -0.07
    ↵		↵
    -0.07
     dessen
    -0.07
     fearful
    -0.07
    POSITIVE LOGITS
     вычис
    0.09
     actuar
    0.08
     computations
    0.08
    ครับ
    0.08
    Pom
    0.08
     Computing
    0.08
    &apos
    0.08
     राजस्थान
    0.07
    latex
    0.07
     computes
    0.07
    Activations Density 0.068%

    No Known Activations