© 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. 108594
    Prev
    Next
    INDEX
    Explanations

    something

    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
    іра
    -0.07
    Represent
    -0.07
     ila
    -0.07
     itr
    -0.07
     dawa
    -0.07
     denomination
    -0.07
     mogą
    -0.07
     Mira
    -0.07
     ressembl
    -0.07
     sheen
    -0.07
    POSITIVE LOGITS
     wrongdoing
    0.11
     acties
    0.08
     knowingly
    0.08
    败
    0.08
    违法
    0.08
     gedrag
    0.08
     நடந்த
    0.08
    ૂ
    0.07
    okwa
    0.07
     commend
    0.07
    Activations Density 0.002%

    No Known Activations