© 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. 99390
    Prev
    Next
    INDEX
    Explanations

    life

    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
     ה
    -0.08
    Worksheet
    -0.08
    Nature
    -0.08
     Nature
    -0.07
    อก
    -0.07
    ڙ
    -0.07
    	d
    -0.07
     mitt
    -0.07
    Spreadsheet
    -0.07
    Output
    -0.07
    POSITIVE LOGITS
    prep
    0.09
    alde
    0.08
     ery
    0.08
    marca
    0.08
     sediments
    0.08
    Creo
    0.08
     depress
    0.08
     Alonso
    0.08
     असे
    0.08
     വേണ്ടി
    0.08
    Activations Density 0.003%

    No Known Activations