© 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. 78919
    Prev
    Next
    INDEX
    Explanations

    Table or list delimiters

    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
     pseudo
    -0.07
     bathrooms
    -0.07
     conj
    -0.07
     for
    -0.07
     PDT
    -0.07
     tils
    -0.07
     if
    -0.07
     needles
    -0.07
     but
    -0.07
     dresser
    -0.07
    POSITIVE LOGITS
    angwa
    0.08
    ㅋㅋ
    0.08
    քում
    0.08
    元棋牌
    0.08
    ancar
    0.08
     环
    0.08
    κοίν
    0.08
    ‍കിയ
    0.07
    %timeout
    0.07
    □□□□□□□□□□□□□□□□
    0.07
    Activations Density 0.042%

    No Known Activations