© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29605
    Prev
    Next
    INDEX
    Explanations

    getline

    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
    adores
    -0.08
     affaire
    -0.08
     disclaim
    -0.08
    authenticated
    -0.08
     erwart
    -0.07
     assure
    -0.07
     guit
    -0.07
     assur
    -0.07
    爷
    -0.07
    ibt
    -0.07
    POSITIVE LOGITS
     precursor
    0.08
    /get
    0.08
     Европ
    0.08
    \App
    0.07
    -Produ
    0.07
    		       
    0.07
    rock
    0.07
    mitted
    0.07
     Пер
    0.07
     Эк
    0.07
    Activations Density 0.001%

    No Known Activations