© 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. 3-RESID-POST-AA
    11. 2673
    Prev
    Next
    INDEX
    Explanations

    Pi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creed
    -0.07
     leg
    -0.07
     barred
    -0.07
    CTYPE
    -0.07
     larg
    -0.07
     chrét
    -0.07
     hem
    -0.07
     brag
    -0.07
     сообщ
    -0.07
     Lin
    -0.07
    POSITIVE LOGITS
     Pey
    0.09
    兵
    0.07
    _SP
    0.07
    謝
    0.07
    _TH
    0.07
    _launcher
    0.07
     Ní
    0.07
    _sh
    0.07
     Cav
    0.07
    ử
    0.07
    Activations Density 0.003%

    No Known Activations