Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87844
    Prev
    Next
    INDEX
    Explanations

    international loans and debt

    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
     anticon
    -0.08
     Birds
    -0.08
    	INT
    -0.08
     hijos
    -0.08
     hoor
    -0.08
    	Int
    -0.08
    ionale
    -0.07
     pec
    -0.07
     offsets
    -0.07
     breasts
    -0.07
    POSITIVE LOGITS
    وض
    0.08
    kn
    0.08
    Kn
    0.08
    ằ
    0.08
     Kilometer
    0.07
     öff
    0.07
    legenheit
    0.07
    Completion
    0.07
     വളരെ
    0.07
    Dial
    0.07
    Activations Density 0.005%

    No Known Activations